Life Prediction System

Abstract

The purpose of the present invention is to provide a lifetime prediction system capable of performing highly reliable lifetime prediction even when the record of events that have occurred in a product is inaccurate. A lifetime prediction system 1 comprises a server device 5 that predicts the lifetime of a product, which is a piece of equipment such as a work machine 2, or an equipment component. The server device 5 includes: an operation information database 52 that stores operation information of each of a plurality of products; a history information database 53 that stores history information indicating a history of event data that is a record of events that have occurred in each of the plurality of products; and a computing process device 54 that predicts product lifetime. The computing process device 54 calculates, on the basis of the operation information and the history information, an event data acquisition rate indicating the percentage of products among the plurality of products that have event data in which the occurrence of events is accurately recorded, and predicts a corrected product lifetime on the basis of the calculated event data acquisition rate.

Description

[Technical Field]

[0001] The present invention relates to a lifespan prediction system for predicting the lifespan of a product. [Background technology]

[0002] BACKGROUND ART A survival analysis method for calculating a survival rate curve of a product is known as a method for predicting the lifespan of a product such as equipment or equipment parts of a work machine (for example, Patent Document 1).

[0003] Patent Document 1 discloses that the Kaplan-Meier method, which is one of the survival time analysis methods, is used to evaluate the lifespan of plant equipment. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Patent No. 6944586 Summary of the Invention [Problem to be solved by the invention]

[0005] The Kaplan-Meier method is an effective method for predicting the lifespan of a product based on the occurrence of "events" such as product repairs (including part replacements). However, the Kaplan-Meier method assumes that events occurring in the product are accurately recorded.

[0006] For example, when plant equipment is the object of observation as in Patent Document 1, inspections are carried out periodically by specialized managers, suppliers, etc., so that events that occur in the plant equipment (repairs or abnormalities in the plant equipment) are accurately recorded.

[0007] On the other hand, with work machines, users may repair them themselves or replace parts with non-genuine parts (hereinafter referred to as "imitations"). Since the replacement history of imitation parts cannot be accurately detected, when a work machine is the subject of observation, it is possible that events that have occurred may not be accurately recorded. As a result, when using the Kaplan-Meier method to predict the lifespan of a product such as a work machine, even though events such as repairs, including part replacements, have occurred, the method may treat the events as not occurring (no repairs have occurred), which could result in an overestimated lifespan.

[0008] In view of the above circumstances, an object of the present invention is to provide a life prediction system that is capable of making highly reliable life predictions even when records of events that occur in a product are inaccurate. [Means for solving the problem]

[0009] In order to solve the above problem, the lifespan prediction system of the present invention is a lifespan prediction system that includes a server device that predicts the lifespan of a product that is equipment or equipment parts, wherein the server device includes an operation information database that stores operation information for each of a plurality of products, a history information database that stores history information indicating a history of event data that is a record of events that have occurred in each of the plurality of products, and a processing device that predicts the lifespan, wherein the processing device calculates an event data acquisition rate that indicates the proportion of products among the plurality of products that have event data in which the occurrence of the event is accurately recorded based on the stored operation information and history information, and predicts the lifespan corrected based on the calculated event data acquisition rate. [Effects of the Invention]

[0010] According to the present invention, it is possible to provide a life prediction system that is capable of making a highly reliable life prediction even if the records of events that occur in a product are inaccurate. [Brief explanation of the drawings]

[0011] [Figure 1] FIG. 1 is a diagram showing the configuration of a life prediction system according to an embodiment of the present invention. [Figure 2] FIG. 2 is a diagram for explaining information stored in the operation information database shown in FIG. [Figure 3] FIG. 2 is a diagram for explaining information stored in the history information database shown in FIG. [Figure 4] FIG. [Figure 5] 2 is a flowchart of a process relating to a life expectancy prediction performed by the arithmetic processing device shown in FIG. [Figure 6] 6 is a flowchart showing details of step s2 shown in FIG. 5. [Figure 7] 6 is a flowchart showing details of step s3 shown in FIG. 5. [Figure 8] FIG. 10 is a diagram showing another example of displaying the life prediction result. [Figure 9] FIG. 10 is a diagram showing another example of displaying the life prediction result. [Figure 10] FIG. 10 is a diagram showing another example of displaying the life prediction result. DETAILED DESCRIPTION OF THE INVENTION

[0012] Hereinafter, embodiments of the present invention will be described with reference to the drawings. Components with the same reference numerals in each embodiment have the same functions in each embodiment unless otherwise specified, and description thereof will be omitted.

[0013] Fig. 1 is a diagram showing the configuration of a lifespan prediction system 1 of this embodiment. Fig. 2 is a diagram explaining information stored in an operation information database 52 shown in Fig. 1. Fig. 3 is a diagram explaining information stored in a history information database 53 shown in Fig. 1. Fig. 4 is a diagram showing a lifespan prediction result.

[0014] The lifespan prediction system 1 is a lifespan prediction system that predicts the lifespan of a product that is equipment or equipment components. The product that is the object of observation by the lifespan prediction system 1 may be a product, such as a work machine 2, for which there is a possibility that an accurate record of events that occur may not be created. Alternatively, the product that is the object of observation by the lifespan prediction system 1 may be a product for which an accurate record of events that occur may be created. In this embodiment, the product that is the object of observation by the lifespan prediction system 1 will be described as being a work machine 2.

[0015] The lifespan prediction system 1 includes a work machine 2, a terminal device 3, a wireless base station 4, and a server device 5. The work machine 2, the terminal device 3, and the server device 5 are connected to each other via a communication network N so that they can communicate with each other.

[0016] The work machine 2 includes an operation information sensor 21, a control device 22, a communication device 23, and a display 24. The operation information sensor 21 is attached to the work machine 2 and collects operation information including operation time, travel distance, hydraulic actuator pressure, etc. The control device 22 has an operation information acquisition unit 221 that acquires operation information from the operation information sensor 21, and an operation information output unit 222 that outputs the acquired operation information to the communication device 23 or the display 24. The communication device 23 communicates with the server device 5 via a wireless base station 4 that constitutes the communication network N. The communication device 23 transmits the acquired operation information of the work machine 2 to at least the server device 5 via the communication network N. The display 24 can display the operation information output from the control device 22, or the lifespan prediction results transmitted from the server device 5, etc.

[0017] The terminal device 3 is a portable terminal device such as a smartphone that has wireless communication functions, a camera function, an input function, a display function, etc. The terminal device 3 may be a terminal device carried by a maintenance person for the work machine 2. The terminal device 3 includes a display 31 configured with a touch screen or the like as an input function and display function. The display 31 displays the inspection items for the work machine 2, and also accepts inspection results input by the maintenance person and stores them in a specified memory area of ​​the terminal device 3. The inspection results include repair records that are records of repairs (including part replacements) performed on the work machine 2. The terminal device 3 transmits the inspection results of the work machine 2 to at least the server device 5 via the communication network N. The display 31 also displays operation information transmitted from the work machine 2, or lifespan prediction results transmitted from the server device 5, etc.

[0018] The server device 5 predicts the lifespan of the work machine 2 that is the object of observation. The server device 5 includes a communication device 51, an operation information database 52, a history information database 53, a calculation processing device 54, and a prediction result database 55.

[0019] The communication device 51 communicates with the work machine 2 or the terminal device 3 via the communication network N.

[0020] The operation information database 52 is a database that stores operation information for each of a plurality of work machines 2. As shown in Fig. 2, the operation information database 52 stores, in association with one another, "machine number" information that identifies each work machine 2, "operating time" information at the time the information was acquired by each work machine 2, and "operating date and time" information that indicates the date and time when the operation information was acquired by each work machine 2. The operation information is transmitted from the work machine 2 to the server device 5 periodically (for example, once a day).

[0021] The history information database 53 is a database that stores history information for each of the multiple work machines 2. The history information indicates a history of event data, which is a record of events that have occurred on each of the multiple work machines 2. An event indicates a change from a normal state in the product being observed. When the product being observed is a work machine 2, an event occurs when the work machine 2 changes from a state in which it is operating normally to a state in which an event such as a part failure or repair has occurred. In other words, an event in this embodiment includes the fact that a work machine 2 has been repaired. The event data in this embodiment includes a repair record of the work machine 2.

[0022] 3, the history information database 53 stores, in association with one another, information on "machine number" that identifies each work machine 2, information on "repair date" which is one of the repair records of each work machine 2, and information on "repair parts" which is one of the repair records of each work machine 2. In addition to the repair records of the work machines 2, the history information database 53 also stores inspection results of the work machines 2 in association with information on "machine number".

[0023] The arithmetic processing device 54 predicts the lifespan of the work machine 2 based on the operation information stored in the operation information database 52 and the history information stored in the history information database 53. Specifically, the arithmetic processing device 54 calculates an event data acquisition rate that indicates the proportion of products among a plurality of work machines 2 that have event data in which the occurrence of an event is accurately recorded, and predicts a corrected lifespan based on the calculated event data acquisition rate.

[0024] The arithmetic processing device 54 is configured to include a processor such as a CPU, and memories such as a ROM and a RAM, and various functions of the arithmetic processing device 54 are realized by the processor executing a program stored in the ROM.

[0025] As shown in FIG. 1, the calculation processing device 54 has an information acquisition unit 541, an extraction unit 542, a first calculation unit 543, a second calculation unit 544, a life prediction unit 545, an inspection timing determination unit 546, and an information output unit 547.

[0026] The information acquisition unit 541 acquires the operation information and history information of the work machine 2 to be observed from the operation information database 52 and history information database 53, respectively. The work machine 2 to be observed is specified by a user such as a maintenance worker by inputting the information into the terminal device 3. At this time, a single work machine 2 may be specified, or multiple work machines 2 having common attributes such as model, vehicle class (weight), etc. may be specified in groups. Designation in groups is preferable as this improves the reliability of lifespan prediction. Note that if there are multiple work machines 2 near the maintenance worker, a list of work machines 2 that are candidates for observation may be automatically displayed on the terminal device 3 based on the position information of the work machines 2 and the terminal device 3, and the maintenance worker may specify any work machine 2 from that list.

[0027] The extraction unit 542 extracts, from among a plurality of work machines 2, long-operating products that have been in operation longer than their design lifespan, based on the operation information of the work machines 2. The operation information includes the operation time of the work machines 2. The work machines 2 to be observed include work machines 2 that fall under the category of long-operating products and work machines 2 that do not fall under the category of long-operating products. The extraction unit 542 calculates the total operation time, which is the sum (cumulative) of the operation times from shipment to the present, based on the operation time included in the operation information. The extraction unit 542 extracts, as long-operating products, work machines 2 whose calculated total operation time has reached, for example, 1.5 times the design lifespan or more. Work machines 2 that fall under the category of long-operating products also include work machines 2 with history information in which a repair record exists and work machines 2 with history information in which a repair record does not exist. Note that the above "1.5 times" is an example based on a standard design lifespan, and the criteria for determining long-operating products may be changed as desired.

[0028] Based on the history information, the first calculation unit 543 calculates the event data acquisition rate, which indicates the proportion of work machines 2 that have event data in which the occurrence of an event is accurately recorded, among the multiple work machines 2 that are the subject of observation. For example, if the number of work machines 2 to be observed is 10,000 and the number of work machines 2 in which the occurrence of an event was accurately observed is 500, the event data acquisition rate is calculated to be (500 / 10,000) = 5%.

[0029] The work machines 2 to be observed include work machines 2 for which there are repair records, which are event data, and work machines 2 for which there are no repair records. A work machine 2 for which there are repair records, which are event data, refers to a work machine 2 for which a repair history exists in its history information, and will also be referred to as a "work machine 2 for which repair records are accurately recorded" below. Work machines 2 for which there are no repair records include, for example, work machines 2 for which there are no repair records despite having actually been repaired, and work machines 2 that have been repaired using imitation repairs, and such work machines 2 will also be referred to as a "work machine 2 for which repair records are not accurately recorded" below. Even if a lifespan prediction is performed using the Kaplan-Meier method including work machines 2 for which repair records are not accurately recorded, it is difficult to perform a highly reliable lifespan prediction. Therefore, in order to perform a lifespan prediction while excluding work machines 2 for which repair records are not accurately recorded, the first calculation unit 543 calculates an event data acquisition rate, which indicates the proportion of work machines 2 for which repair records are accurately recorded among the work machines 2 to be observed.

[0030] Here, all long-operating products with a total operating time of 1.5 times or more the design lifespan should ideally have repair records. However, in reality, long-operating products include both long-operating products with no repair records and long-operating products with repair records due to factors such as the influence of repairs using imitation products. The proportion of long-operating products with repair records among long-operating products is highly likely to be equal to the proportion of work machines 2 with accurately recorded repair records among the observed work machines 2. Therefore, the first calculation unit 543 of this embodiment calculates the proportion of long-operating products with repair records among the long-operating products extracted by the extraction unit 542 as the event data acquisition rate. This allows the first calculation unit 543 of this embodiment to accurately calculate the event data acquisition rate.

[0031] Specifically, the first calculation unit 543 of this embodiment calculates the event data acquisition rate F r In Formula 1, F r indicates the event data acquisition rate, A indicates the number of long-operating products with repair records, and B indicates the number of long-operating products without repair records. The denominator (A+B) on the right side of Equation 1 indicates the total number of long-operating products extracted by the extraction unit 542.

[0032]

number

[0033] In addition, in the present embodiment, when the history information for each long-operating product includes multiple repair records, the first calculation unit 543 counts the first repair record (specifies it as the calculation target) and calculates the event data acquisition rate. The first repair record for the work machine 2 indicates the first repair performed on a given part within the work machine 2 since the work machine 2 was shipped. Some work machines 2 may be repaired multiple times. For example, if a part of the work machine 2 breaks down and is repaired (first repair date), and then the part breaks down again after this repair and is repaired again, the repair record for the work machine 2 will include multiple repair records. The first calculation unit 543 in the present embodiment identifies the first repair record with the oldest first repair date recorded among the multiple repair records for each long-operating product, and counts the identified first repair record to calculate the number of long-operating products for which a repair record exists. This eliminates the need for the first calculation unit 543 to duplicate repair records, thereby enabling the event data acquisition rate to be calculated accurately.

[0034] The second calculation unit 544 calculates the inter-failure operation time, which is the operation time of the work machine 2 from the shipment date to the first repair record, based on the operation information and history information. Specifically, the second calculation unit 544 identifies the first repair record of each of the multiple work machines 2 to be observed, and identifies the first repair date from the identified first repair record. Then, the second calculation unit 544 calculates the operation time from the shipment date to the first repair date of each of the multiple work machines 2 to be observed as the inter-failure operation time.

[0035] The lifespan prediction unit 545 predicts the lifespan of the work machine 2 using the Kaplan-Meier method. At this time, the lifespan prediction unit 545 predicts a corrected lifespan based on the event data acquisition rate calculated by the first calculation unit 543, and calculates the corrected lifespan prediction result. The corrected lifespan prediction result means a lifespan prediction result that has been corrected from a lifespan prediction result calculated by directly applying the Kaplan-Meier method (hereinafter also referred to as the "lifespan prediction result before correction"). Specifically, the lifespan prediction unit 545 corrects the surviving number of the multiple work machines 2 that are the observation targets, according to the event data acquisition rate calculated by the first calculation unit 543. Then, the lifespan prediction unit 545 estimates the survival rate of the multiple work machines 2 using the Kaplan-Meier method from the corrected surviving number of work machines 2 and the operating time between failures calculated by the second calculation unit 544. In this way, the lifespan prediction unit 545 can calculate the corrected lifespan prediction result. The number of surviving work machines 2 refers to the number of work machines 2 that are not broken down among the multiple work machines 2 that are being observed. The survival rate of work machines 2 refers to the proportion of the number of work machines 2 that are not broken down to the total number of the multiple work machines 2 that are being observed.

[0036] The uncorrected life expectancy prediction result calculated by directly applying the Kaplan-Meier method is expressed by Equation 2. In Equation 2, S^ on the left side KM (t) indicates the estimated survival rate of work machine 2 during the total operating time t. i indicates the number of working machines 2 that have survived up to the total operating time t (survival number). i indicates the number of work machines 2 that have broken down during the total operating time t.

[0037]

number

[0038] In contrast to this, the life expectancy prediction unit 545 of this embodiment calculates the number of surviving working machines 2 n as shown in Equation 3. i The event data acquisition rate F rThe survival rate of the work machine 2 is estimated by correcting the S^ on the left side of the formula 3. AKM (t) indicates the estimated survival rate of work machine 2 after correction.

[0039]

number

[0040] The lifespan prediction unit 545 can calculate lifespan prediction results as shown in Fig. 4. The vertical axis of Fig. 4 indicates the estimated survival rate of the work machine 2, and the horizontal axis of Fig. 4 indicates the total operating time of the work machine 2. In Fig. 4, the corrected lifespan prediction results are shown by a solid line, and the lifespan prediction results before correction are shown by a dashed line. As shown in Fig. 4, the lifespan prediction results before correction show that the number of work machines 2 that have been repaired using imitation machines and the number of work machines 2 that have actually been repaired but for which no repair records exist are proportional to the survival rate (n i ) may not be zero even after the total operating time has elapsed. In contrast, the corrected lifespan prediction results are based on the event data acquisition rate (F r ) to determine the number of surviving work machines (n i ), the estimated survival rate reaches zero after a long period of time has elapsed. Comparing the lifespan prediction result after correction with the lifespan prediction result before correction, it is found that the lifespan prediction result after correction using Equation 3 by lifespan prediction unit 545 is valid.

[0041] The inspection time determination unit 546 determines when the work machine 2 should be inspected based on the corrected lifespan prediction result calculated by the lifespan prediction unit 545. For example, the inspection time determination unit 546 can regard the time T1 when the estimated value of the survival rate of the work machine 2, which is the corrected lifespan prediction result, reaches a first threshold value S1 (e.g., 75%) as the time when the remaining lifespan of a certain work machine 2 will reach the first threshold value S1. The inspection time determination unit 546 determines the time T1 when the estimated value of the survival rate of the work machine 2 reaches the first threshold value S1 as the time when inspection of the work machine 2 is recommended. The inspection time determination unit 546 determines the time T2 when the estimated value of the survival rate of the work machine 2, which is the corrected lifespan prediction result, reaches a second threshold value S2 (e.g., 50%) as the time when inspection of the work machine 2 is strongly recommended. Furthermore, the inspection timing determination unit 546 determines that the time T3 at which the estimated value of the survival rate of the work machine 2, which is the corrected lifespan prediction result, reaches a third threshold value S3 (for example, 25%) is the time to urgently inspect the work machine 2. In this way, the inspection timing determination unit 546 determines the time at which the work machine 2 should be inspected, based on the corrected lifespan prediction result calculated by the lifespan prediction unit 545.

[0042] In this embodiment, the service life of the work machine 2 at the time of shipment is set to 100%, and the current service life of the work machine 2 is expressed as a percentage according to the total operating time since shipment, and this percentage index is also referred to as the "service life progress degree." In this embodiment, the estimated value of the survival rate of the work machine 2 estimated by the service life prediction unit 545 is regarded as the service life progress degree of the work machine 2.

[0043] The information output unit 547 registers the life prediction result calculated by the life prediction unit 545 and the inspection timing determination result acquired by the inspection timing determination unit 546 in the prediction result database 55 and outputs them to the communication device 51. The communication device 51 transmits the life prediction result and the inspection timing determination result to at least the terminal device 3 via the communication network N. The terminal device 3 displays the life prediction result and the inspection timing determination result on the display 31 in a graph format as shown in Fig. 4, for example. Other display examples of the life prediction result and the like will be described later with reference to Figs. 8 to 10.

[0044] The prediction result database 55 stores the life prediction results calculated by the life prediction unit 545 and the inspection timing determination results acquired by the inspection timing determination unit 546. The life prediction results and the like stored in the prediction result database 55 are provided to the arithmetic processing device 54 and are used to improve the reliability of life predictions made by the arithmetic processing device 54.

[0045] The life prediction unit 545 may calculate not only the corrected life prediction result indicated by Equation 3, but also the uncorrected life prediction result indicated by Equation 2. In this case, the information output unit 547 outputs the corrected life prediction result and the uncorrected life prediction result to the communication device 51. The communication device 51 transmits the corrected life prediction result and the uncorrected life prediction result to the terminal device 3. The terminal device 3 displays the corrected life prediction result and the uncorrected life prediction result on the display 31.

[0046] Furthermore, the lifespan prediction unit 545 may predict the lifespan of the work machine 2 using a method other than the Kaplan-Meier method, such as the Nelson-Aalen method.

[0047] FIG. 5 is a flowchart of a process relating to life prediction performed by the arithmetic processing device 54 shown in FIG.

[0048] In step s1, the information acquisition unit 541 of the arithmetic processing device 54 acquires the operation information and history information of the multiple work machines 2 to be observed from the operation information database 52 and history information database 53, respectively.

[0049] In step s2, the extraction unit 542 of the arithmetic processing device 54 extracts long-term operating products from among the plurality of work machines 2. Details of step s2 will be described later with reference to FIG.

[0050] In step s3, the first calculation unit 543 of the calculation processing device 54 calculates the number of first repairs, which is the number of first repair records counted for each of the extracted long-term operating products. The number of first repairs corresponds to the number A of long-term operating products for which repair records exist in Equation 1. Details of step s3 will be described later with reference to FIG. 7.

[0051] In step s4, the first calculation unit 543 of the arithmetic processing device 54 calculates the event data acquisition rate.

[0052] In step s5, the second calculation section 544 of the arithmetic processing device 54 identifies the first repair date for each of the multiple work machines 2 that are the observation targets.

[0053] In step s6, the second calculation section 544 of the arithmetic processing device 54 calculates the operating time between failures for each of the plurality of work machines 2.

[0054] In step s7, the life prediction unit 545 of the arithmetic processing device 54 predicts the life of the work machine 2. Thereafter, the arithmetic processing device 54 ends the processing shown in FIG.

[0055] After step s1, the arithmetic processing device 54 may execute the processes from step s2 to step s4 and the processes from step s5 to step s6 in parallel, and then execute step s7. Alternatively, after step s1, the arithmetic processing device 54 may first execute the processes from step s5 to step s6, then execute the processes from step s2 to step s4, and then execute step s7.

[0056] FIG. 6 is a flowchart showing the details of step s2 shown in FIG.

[0057] In step s21, the extraction unit 542 of the arithmetic processing device 54 calculates the total operating time of each of the multiple work machines 2 that are the observation targets.

[0058] In step s22, the extraction unit 542 of the calculation processing device 54 determines whether the total operating time of the work machine 2 is 1.5 times or more the design life. If the total operating time is 1.5 times or more the design life of the work machine 2, the extraction unit 542 proceeds to step s23. If the total operating time is not 1.5 times or more the design life of the work machine 2, the extraction unit 542 proceeds to step s24.

[0059] In step s23, the extraction section 542 of the arithmetic processing device 54 extracts the working machine 2 that is the subject of the determination process in step s22 as a long-term operating product.

[0060] In step s24, the extraction unit 542 of the calculation processing device 54 determines whether or not the determination process of step s22 has been performed for all of the work machines 2 that are the observation targets. If the determination process of step s22 has been performed for all of the work machines 2, the extraction unit 542 ends this process shown in Figure 6 and proceeds to step s3 in Figure 5. If the determination process of step s22 has not been performed for all of the work machines 2, the extraction unit 542 proceeds to step s22 in Figure 5.

[0061] FIG. 7 is a flowchart showing the details of step s3 shown in FIG.

[0062] In step s31, the first calculation unit 543 of the arithmetic processing device 54 identifies the first repair record of each of the extracted long-operating products.

[0063] In step s32, the first calculation unit 543 of the calculation processing device 54 counts the identified first repair records to calculate the number of first repairs. After that, the first calculation unit 543 ends this process shown in Fig. 7 and proceeds to step s4 in Fig. 5.

[0064] Fig. 8 is a diagram showing another example of displaying a lifespan prediction result, etc. Fig. 9 is a diagram showing another example of displaying a lifespan prediction result, etc. Fig. 10 is a diagram showing another example of displaying a lifespan prediction result, etc.

[0065] The terminal device 3 can display the life prediction result and the inspection timing determination result on the display 31 in a display format as shown in FIG. 8. For example, as shown on the left side of FIG. 8, the terminal device 3 can display an alert 311 indicating the urgency of the inspection timing depending on the current remaining life of the work machine 2, a tab 312 for displaying detailed life prediction results, etc., and a tab 313 for setting the display format of the display 31. When the user taps the tab 312, the terminal device 3 displays the detailed life prediction result, etc., in the display format of, for example, a graph 314, as shown on the right side of FIG. 8. Furthermore, as shown on the right side of FIG. 8, the terminal device 3 can display a tab 315 for switching between displaying the life prediction result before correction and displaying the life prediction result after correction. When the user taps the tab 315, the terminal device 3 can switch between displaying the life prediction result before correction and the life prediction result after correction. The terminal device 3 can also simultaneously display the life prediction result before correction and the life prediction result after correction on the same screen for comparison.

[0066] As described above, the lifespan progression of a work machine 2 is an index that expresses an estimate of the current lifespan of the work machine 2 as a percentage according to the total operating time since shipment, with the lifespan at the time of shipment of the work machine 2 being 100%. If the lifespan progression is 50%, it is estimated that approximately half of the work machines 2 will break down, taking into account past repair records, etc. As the lifespan progression decreases, the urgency of inspection increases, so the server device 5 (inspection timing determination unit 546 of the processing device 54) can set multiple thresholds for the remaining lifespan according to the urgency of inspection, and can display a different alert 311 on the terminal device 3 each time the remaining lifespan reaches each threshold. For example, when the lifespan progression reaches 75%, the terminal device 3 can display the alert 311 stating "Inspection Recommended" because there is relatively ample time left in the lifespan. For example, when the lifespan progression reaches 50%, the terminal device 3 can display the alert 311 stating "Important," which strongly recommends inspection. For example, when the lifespan progress rate reaches 25%, the terminal device 3 can display an alert 311 saying "urgent" indicating that an inspection is required urgently.

[0067] Furthermore, to make it easier for the user to understand the current stage of lifespan progression, the terminal device 3 can display the current lifespan progression as a horizontal line S in the graph 314, and can display the inspection timing corresponding to the current lifespan progression as a vertical line T in the graph 314, as shown on the right side of FIG. 8 . In this case, the terminal device 3 can display the horizontal line S and the vertical line T in different colors depending on the urgency of the inspection. For example, before the lifespan progression reaches "inspection recommended," the terminal device 3 can display the horizontal line S and the vertical line T in green. For example, after the lifespan progression reaches "inspection recommended" and before it reaches "critical," the terminal device 3 can display the horizontal line S and the vertical line T in blue. For example, after the lifespan progression reaches "critical" and before it reaches "urgent," the terminal device 3 can display the horizontal line S and the vertical line T in yellow. For example, after the lifespan progression reaches "urgent," the terminal device 3 can display the horizontal line S and the vertical line T in red.

[0068] Furthermore, the terminal device 3 can display, in a pop-up window that appears near the horizontal line S or the vertical line T, the useful life of the work machine 2 corresponding to the current progress of its lifespan or the date on which that useful life will end, or the date on which the work machine 2 will be inspected according to the current progress of its lifespan. For example, the terminal device 3 can display, in the pop-up window, a message saying "within six months (x month x day)" as the useful life of the work machine 2 corresponding to the current progress of its lifespan (the date on which the useful life will end). Note that the display format is not limited to messages or pop-ups, and a calendar display, for example, may also be used. For example, when there is ample time left in the useful life, a simple display such as "three months before" may be used, and as the end of the useful life approaches, a more specific date may be displayed.

[0069] Furthermore, the terminal device 3 can also display the life prediction results and the inspection timing determination results on the display 31 in the display format of a table 316 as shown in FIG. 9, instead of the graph 314 shown on the right side of FIG.

[0070] Furthermore, the terminal device 3 can display the life prediction result and the inspection timing determination result on the display 31 in a display format other than the display formats shown in Figs. 8 and 9. For example, as shown in Fig. 10, the terminal device 3 can display the life prediction result and the inspection timing determination result in the form of a message 317. The message 317 may be sent to the terminal device 3 by email, SMS, or the like from the server device 5, and may be displayed as a pop-up on the terminal device 3. The message 317 includes the life progression of the work machine 2 and an indication of the inspection timing. The transmission frequency and display frequency of the message 317 may be a frequency at which the message is sent and displayed every time the life progression reaches a threshold value, or a frequency at which the message is sent and displayed at regular intervals, such as once a week. The transmission frequency and display frequency of the message 317 can be changed as desired by the user to improve user convenience.

[0071] The terminal device 3 can display the life prediction results and the inspection timing determination results by arbitrarily combining the display examples of Figures 8 to 10. The terminal device 3 can display the life prediction results and the inspection timing determination results by arbitrarily changing the way in which the display examples of Figures 8 to 10 are combined, depending on the user's settings. Also, although Figures 8 to 10 have described an example in which the life prediction results and the inspection timing determination results are displayed on the display 31 of the terminal device 3, the life prediction results and the inspection timing determination results may be displayed not only on the terminal device 3 but also on the display 24 of the work machine 2.

[0072] As described above, the lifespan prediction system 1 of this embodiment is a lifespan prediction system including a server device 5 that predicts the lifespan of products that are equipment or equipment components such as the work machine 2. The server device 5 includes an operation information database 52 that stores operation information for each of the multiple products to be observed, and a history information database 53 that stores history information indicating the history of event data that is a record of events that have occurred in each of the multiple products. The server device 5 includes a calculation processing device 54 that predicts the lifespan of the products. The calculation processing device 54 calculates an event data acquisition rate that indicates the proportion of products among the multiple products that have event data in which the occurrence of an event is accurately recorded, based on the operation information stored in the operation information database 52 and the history information stored in the history information database 53. The calculation processing device 54 predicts the corrected lifespan of the products based on the calculated event data acquisition rate.

[0073] As a result, the lifespan prediction system 1 of this embodiment can predict a lifespan even if events that have occurred in a product are not accurately recorded. Therefore, the lifespan prediction system 1 of this embodiment can predict a lifespan with high reliability even if the records of events that have occurred are inaccurate.

[0074] Furthermore, in the lifespan prediction system 1 of this embodiment, the arithmetic processing device 54 predicts the lifespan of the product using the Kaplan-Meier method.

[0075] This allows the lifespan prediction system 1 of this embodiment to use the Kaplan-Meier method, an existing lifespan prediction method, and therefore the lifespan prediction system 1 of this embodiment can easily perform highly reliable lifespan prediction even if the records of events that have occurred are inaccurate.

[0076] Furthermore, in the lifespan prediction system 1 of this embodiment, the event data includes product repair records. The arithmetic processing device 54 has an extraction unit 542 that extracts, from the multiple products, long-operating products that have been operating longer than their design lifespan, based on operation information stored in the operation information database 52. The arithmetic processing device 54 has a first calculation unit 543 that calculates, as an event data acquisition rate, the proportion of long-operating products for which repair records exist, among the long-operating products extracted by the extraction unit 542, based on history information stored in the history information database 53. The arithmetic processing device 54 has a lifespan prediction unit 545 that predicts the corrected product lifespan based on the event data acquisition rate calculated by the first calculation unit 543.

[0077] As a result, the lifespan prediction system 1 of this embodiment can accurately calculate the event data acquisition rate, which indicates the percentage of products for which the occurrence of events is accurately recorded.The lifespan prediction system 1 of this embodiment can perform lifespan prediction based on the accurate event data acquisition rate, thereby improving the accuracy of lifespan prediction.Therefore, the lifespan prediction system 1 of this embodiment can perform more reliable lifespan prediction even if the record of the events that have occurred is inaccurate.

[0078] Furthermore, in the lifespan prediction system 1 of this embodiment, the arithmetic processing device 54 further includes a second calculation unit 544 that calculates an inter-failure operating time, which is the operating time of the product from the shipment of the product to the first repair record, based on the operation information and the history information. The lifespan prediction unit 545 corrects the survival number of the multiple products in accordance with the event data acquisition rate calculated by the first calculation unit 543. The lifespan prediction unit 545 estimates the survival rate of the multiple products using the corrected survival number and the calculated inter-failure operating time using the Kaplan-Meier method, thereby calculating the corrected lifespan prediction result.

[0079] As a result, the lifespan prediction system 1 of this embodiment can predict lifespan by expanding the scope of application of the Kaplan-Meier method, which is an effective lifespan prediction method, to cases where the records of events that occur in the product are inaccurate. Therefore, the lifespan prediction system 1 of this embodiment can easily and reliably perform highly reliable lifespan prediction even when the records of events that occur are inaccurate.

[0080] Furthermore, in the lifespan prediction system 1 of this embodiment, when the history information of each long-term operating product includes multiple repair records, the first calculation unit 543 counts the first repair record and calculates the event data acquisition rate.

[0081] This eliminates the need to count repair records twice, allowing the lifespan prediction system 1 of this embodiment to accurately calculate the event data acquisition rate. Therefore, the lifespan prediction system 1 of this embodiment can perform more reliable lifespan predictions even when the records of events that have occurred are inaccurate.

[0082] Furthermore, in the lifespan prediction system 1 of this embodiment, the arithmetic processing device 54 has an inspection timing determination unit 546 that determines when to inspect the product based on the corrected lifespan prediction result.

[0083] As a result, the lifespan prediction system 1 of this embodiment can accurately determine when to inspect a product while making a highly reliable lifespan prediction even if the record of an event that has occurred is inaccurate.

[0084] Furthermore, the lifespan prediction system 1 of this embodiment further includes a terminal device 3 connected to the server device 5 via a communication network N. The server device 5 further includes a communication device 51 that communicates with the terminal device 3. The arithmetic processing device 54 calculates a corrected lifespan prediction result and also calculates an uncorrected lifespan prediction result that indicates the lifespan before correction. The communication device 51 transmits the corrected lifespan prediction result and the uncorrected lifespan prediction result to the terminal device 3. The terminal device 3 displays the corrected lifespan prediction result and the uncorrected lifespan prediction result.

[0085] As a result, the lifespan prediction system 1 of this embodiment can present the lifespan prediction results before and after correction to the user, thereby improving convenience for users who want to compare the lifespan prediction results before and after correction. Therefore, the lifespan prediction system 1 of this embodiment can improve user convenience while performing highly reliable lifespan predictions even if the record of the events that have occurred is inaccurate.

[0086] Although the embodiments of the present invention have been described in detail above, the present invention is not limited to the above embodiments, and various modifications can be made without departing from the spirit of the present invention as defined in the claims. In the present invention, the configuration of one embodiment can be added to the configuration of another embodiment, the configuration of one embodiment can be replaced with the configuration of another embodiment, or part of the configuration of one embodiment can be deleted. [Explanation of symbols]

[0087] 1... life prediction system, 2... work machine, 3... terminal device, 5... server device, 51... communication device, 52... operation information database, 53... history information database, 54... arithmetic processing device, 541... information acquisition unit, 542... extraction unit, 543... first calculation unit, 544... second calculation unit, 545... life prediction unit, 546... inspection timing determination unit

Claims

1. A lifespan prediction system including a server device for predicting the lifespan of a product that is a device or a device part, The server device an operation information database that stores operation information of each of a plurality of products; a history information database that stores history information indicating a history of event data that is a record of events that occurred in each of the plurality of products; a processing unit for predicting the lifespan, The arithmetic processing device calculates an event data acquisition rate indicating a ratio of products having the event data in which the occurrence of the event is accurately recorded among the plurality of products, based on the stored operation information and history information, and predicts the corrected lifespan based on the calculated event data acquisition rate. A life prediction system characterized by:

2. The computing device predicts the lifespan using the Kaplan-Meier method.

2. The life prediction system according to claim 1,

3. the event data includes a repair record of the product; The arithmetic processing device an extracting unit that extracts, from the plurality of products, long-term operating products that have been operating longer than their design lifespans, based on the stored operation information; a first calculation unit that calculates, based on the stored history information, a ratio of the long-operating products for which the repair records exist among the extracted long-operating products as the event data acquisition rate; a lifespan prediction unit that predicts the corrected lifespan based on the calculated event data acquisition rate; 2. The life prediction system according to claim 1,

4. The arithmetic processing device a second calculation unit that calculates an inter-failure operation time, which is an operation time of the product from the time the product is shipped to the time the first repair record is recorded, based on the stored operation information and history information; The life prediction unit correcting the survival number of the plurality of products according to the calculated event data acquisition rate; The corrected survival rate of the plurality of products is estimated using the Kaplan-Meier method from the corrected survival number and the calculated operating time between failures, thereby calculating the corrected lifespan prediction result.

4. The life prediction system according to claim 3.

5. The lifespan prediction system of claim 3, characterized in that when the history information of each of the long-term operating products includes multiple repair records, the first calculation unit counts the first repair record and calculates the event data acquisition rate.

6. The arithmetic processing device has an inspection timing determination unit that determines when the product should be inspected based on the corrected life prediction result.

2. The life prediction system according to claim 1,

7. The system further includes a terminal device connected to the server device via a communication network, the server device further includes a communication device that communicates with the terminal device; the arithmetic processing device calculates a corrected life prediction result and also calculates an uncorrected life prediction result; the communication device transmits the corrected lifespan prediction result and the uncorrected lifespan prediction result to the terminal device; The life prediction system according to claim 1 , wherein the terminal device displays the corrected life prediction result and the uncorrected life prediction result.

Images