Prediction device, prediction method, and prediction program

Abstract

The purpose of the present invention is to provide a prediction device, a prediction method, and a prediction program that are capable of predicting the required replacement time of an oil check valve mounted in a vehicle. A prediction device, a prediction method, and a prediction program according to the present disclosure are provided with: an acquisition unit that acquires, from a storage unit, first information relating to an operation history of an oil check valve, and second information relating to an oil temperature history of oil in an oil circulation path; and a calculation unit that calculates, on the basis of the first information and the second information, an index relating to the replacement-requiring time of the oil check valve using a previously learned identifier model.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to a prediction device, a prediction method, and a prediction program. BACKGROUND

[0002] Generally, an oil check valve (hereinafter also referred to as "OCV") for switching a flow destination of engine oil is provided in an oil circulation passage of a vehicle. Such an oil check valve is, for example, disposed downstream of an oil cooler in the oil circulation passage and functions as a switching valve that causes oil in the oil circulation passage to flow to an oil jet passage connected to an oil jet nozzle for cooling pistons of an engine (see, for example, Patent Literature 1).

[0003] PRIOR ART DOCUMENTS

[0004] PATENT LITERATURE

[0005] Patent Literature 1: Japanese Patent Application Publication No. 2014-98345 SUMMARY

[0006] PROBLEMS TO BE SOLVED BY THE INVENTION

[0007] However, in such an oil check valve, a bobbin member of an electromagnetic coil that causes the oil check valve to operate is made of a resin material (for example, a polyamide resin). Such a resin material is generally deteriorated by heat.

[0008] In a case where the resin material in the oil check valve is deteriorated, there is a possibility that oil seepage from the oil check valve occurs. In a case where the damage of the oil seepage is expanded, since there is a possibility that the oil leaks to the inside or outside of the vehicle, it is necessary to replace the oil check valve at an early stage.

[0009] However, at present, the occurrence of the oil seepage from the oil check valve can be found only by confirming an actual product at an inspection site or the like, and it is difficult to predict the timing of the occurrence in advance.

[0010] The present invention has been achieved in view of the above-described problems, and an object thereof is to provide a prediction device, a prediction method, and a prediction program capable of predicting a replacement required timing of an oil check valve mounted on a vehicle.

[0011] SOLUTION TO PROBLEM

[0012] The main content of the present disclosure that solves the above-described technical problem is a prediction device that predicts a replacement required timing of an oil check valve provided in an oil circulation passage of a vehicle, the prediction device including:

[0013] an acquisition section that acquires first information and second information from a storage section, the first information being information related to an operation history of the oil check valve, and the second information being information related to an oil temperature history of oil in the oil circulation passage; and

[0014] an operation section that calculates, based on the first information and the second information, an index related to the replacement required period of the oil check valve using a recognizer model that has been learned in advance.

[0015] In another aspect, a prediction method that predicts a replacement required period of an oil check valve provided in an oil circulation passage of a vehicle includes the following processing:

[0016] processing of acquiring, from a storage section, first information that is information related to an operation history of the oil check valve and second information that is information related to an oil temperature history of oil in the oil circulation passage; and

[0017] processing of calculating, based on the first information and the second information, an index related to the replacement required period of the oil check valve using a recognizer model that has been learned in advance.

[0018] In another aspect, a computer-readable storage medium has stored thereon a prediction program that predicts a replacement required period of an oil check valve provided in an oil circulation passage of a vehicle, the prediction program realizing the following processing when executed by a processor:

[0019] processing of acquiring, from a storage section, first information that is information related to an operation history of the oil check valve and second information that is information related to an oil temperature history of oil in the oil circulation passage; and

[0020] processing of calculating, based on the first information and the second information, an index related to the replacement required period of the oil check valve using a recognizer model that has been learned in advance.

[0021] The prediction device according to the present application can predict a replacement required period of an oil check valve mounted on a vehicle. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 is a diagram showing an example of a structure of a vehicle.

[0023] Figure 2 is a diagram showing an example of an overall structure of an oil supply device.

[0024] Figure 3 is a diagram showing an example of a structure of an ECU.

[0025] Figure 4 is a diagram showing an example of oil temperature history data of an oil circulation passage.

[0026] Figure 5 is a diagram showing an example of operation history data of an oil check valve.

[0027] Figure 6 This is a graph showing the results of an investigation into the correlation between various parameters and the vehicles with / without oil check valve replacements.

[0028] Figure 7 This is a graph showing the results of a market survey on the types of loading equipment on vehicles and the frequency of replacement or non-replacement of oil check valves (i.e., whether a malfunction occurs or not).

[0029] Figure 8 This is a diagram illustrating an example of the structure of a recognizer model.

[0030] Figure 9 This is a flowchart illustrating an example of the operation of an ECU.

[0031] Figure 10 It is an illustrative explanation Figure 9 The flowchart is shown.

[0032] Figure 11 This is an example of a display screen shown on the display unit of the ECU.

[0033] Figure 12 This is an example of a display showing the progression of the probability of adverse events occurring.

[0034] Explanation of reference numerals in the attached figures

[0035] 2 oil pan

[0036] 3. Oil circulation path

[0037] 6. Fuel Injector Fuel Line

[0038] 10 Oil pumps

[0039] 20 Oil Cooler

[0040] 30 Oil Filter

[0041] 40 Oil check valve

[0042] 50 Oil Temperature Sensor

[0043] 100ECU

[0044] 102ROM

[0045] 103 RAM

[0046] 104 External storage devices

[0047] 105 Ministry of Communications

[0048] 106 Input Section

[0049] 107 Display Department

[0050] Vehicle C

[0051] Ca loading equipment

[0052] Cb engine

[0053] CBB oil supply unit

[0054] D1 Recognizer Model

[0055] D2 oil temperature history data

[0056] D3 Work history data

[0057] D4 Driving History Data Detailed Implementation

[0058] Hereinafter, preferred embodiments of the present invention will be described in detail with reference to the accompanying drawings. It should be noted that in this specification and the accompanying drawings, structural elements having substantially the same function are omitted from repeated description by using the same reference numerals.

[0059] <Vehicle Overall Structure>

[0060] The structure of a vehicle (hereinafter referred to as "vehicle C") and a prediction device mounted on the vehicle C according to one embodiment of the present invention will now be described.

[0061] It should be noted that the predictive device in this embodiment consists of an ECU (Engine Control Unit) that operates the oil check valve mounted on the vehicle, and predicts when the oil check valve needs to be replaced. However, the predictive device does not necessarily need to be mounted on the vehicle; for example, it can be configured by an external management computer.

[0062] Figure 1 This is a diagram illustrating an example of the structure of vehicle C.

[0063] Vehicle C is, for example, a large vehicle equipped with loading equipment Ca. Vehicle C has an engine Cb and an oil supply device Cbb for supplying oil for piston cooling to the engine Cb.

[0064] Figure 2 This is a diagram illustrating an example of the overall structure of the oil supply unit Cbb. Figure 3 This is a diagram illustrating an example of the structure of ECU100.

[0065] The fuel supply unit Cbb includes an oil pan 2, an oil circulation circuit 3, a fuel injector circuit 6, an oil pump 10, an oil cooler 20, an oil filter 30, an oil check valve 40, an oil temperature sensor 50, and an ECU 100.

[0066] Oil pump 10 draws oil stored in oil pan 2 and pumps it into oil circulation path 3. Oil pump 10 is, for example, a mechanical oil pump driven by the rotation of the crankshaft of engine Cb.

[0067] Oil circulation path 3 is the oil circulation path that circulates the oil supplied by oil pump 10. In oil circulation path 3, an oil filter 30, an oil cooler 20, and an oil check valve 40 are installed from the upstream side. Oil circulation path 3 connects to the fuel injector oil passage 6 at the location of the oil check valve 40. The fuel injector oil passage 6 is the oil passage connected to the fuel injectors used for cooling the pistons of engine Cb.

[0068] The oil cooler 20 cools the oil in the oil circulation path 3 and sends oil to the oil check valve 40.

[0069] The oil check valve 40 switches the oil path, that is, it switches the destination of the oil supplied from the oil cooler 20 between the fuel injector oil path 6 and the return path of the oil circulation path 3. Specifically, the oil check valve 40 activates its built-in electromagnet according to the control signal from the ECU 100 to switch the destination of the oil in the oil circulation path 3.

[0070] The structure of the oil check valve 40 is the same as that of the previously known structure, so the description is omitted here.

[0071] The oil check valve 40, for example, has a spool valve that is axially reciprocating within an internal space provided inside the housing. Furthermore, the oil check valve 40 switches the oil circuit by actuating the spool valve using an electromagnet integrally disposed with the spool valve, that is, switching the destination of the oil in the oil circulation path 3 between the injector oil circuit 6 side and the return path side of the oil circulation path 3.

[0072] It should be noted that in the oil check valve 40, a resin material (e.g., a polyamide resin) is used as the spool material for the coil constituting the electromagnet. It should also be noted that this spool material functions as a sealant for the oil within the oil check valve 40.

[0073] The oil check valve 40 is electrically connected to the ECU 100 and is controlled by the control current supplied from the ECU 100. When no control current is supplied to its own electromagnet, the oil check valve 40 supplies oil from the oil cooler 20 to the fuel injector oil passage 6. Conversely, when the oil check valve 40 supplies control current to its own electromagnet, the electromagnet drives the internal spool valve to move to one side, supplying oil from the oil cooler 20 to the return path side of the oil circulation path 3. In other words, the oil check valve 40 in this embodiment is controlled such that when energized ON, the fuel injector is OFF, and when energized OFF, fuel injection is performed.

[0074] An oil temperature sensor 50 is disposed in the oil circulation path 3 to continuously detect the oil temperature in the oil circulation path 3. Here, in this embodiment, the oil temperature sensor 50 is disposed downstream of the oil cooler 20 in the oil circulation path 3 and detects the oil temperature of the oil passing through the oil check valve 40. The oil temperature sensor 50 is electrically connected to the ECU 100 and transmits the detected oil temperature to the ECU 100.

[0075] ECU100 is a computer with main components such as CPU101, ROM102, RAM103, external storage device (e.g., flash memory)104, communication unit (e.g., Internet-connected communication module)105, input unit (e.g., keyboard or mouse)106 and display unit (e.g., liquid crystal display)107.

[0076] The functions of ECU100 described later are implemented, for example, by CPU101 referring to processing programs or various data stored in ROM102, RAM103, external storage device 104, etc. It should be noted that the processing performed by CPU101 is equivalent to the functions of the "acquisition unit" and "processing unit" of the present invention.

[0077] The external storage device 104 stores the pre-learned recognizer model D1, the oil temperature history data D2 of the oil circulation circuit 3, the working history data D3 of the oil check valve 40, and the driving history data D4 of the vehicle C.

[0078] Here, the oil temperature history data D2 of the oil circulation circuit 3, the working history data D3 of the oil check valve 40, and the driving history data D4 of the vehicle C are data that are sequentially stored in the external storage device 104 while the vehicle C is in motion. In addition, the recognizer model D1 is, for example, a recognizer model that has undergone learning processing and parameter adjustment in advance (details will be described later).

[0079] <Basic Concepts for Predicting the Replacement Period of Oil Check Valves>

[0080] The ECU 100 of this embodiment has the function of predicting when the oil check valve 40 needs to be replaced. First, the basic concept of the method for predicting when the oil check valve 40 needs to be replaced in the ECU 100 of this embodiment will be explained.

[0081] The inventors of this invention recognized the importance of quantifying the thermal damage to the spool material of the oil check valve 40 when accurately predicting the replacement period required for the oil check valve 40, and investigated the influencing factors causing thermal damage to this spool material. This is because oil seepage from the spool material is primarily caused by the thermal degradation of the resin material of the structural spool material.

[0082] The results showed that the thermal damage to the spool material of the oil check valve 40 was caused by (1) thermal damage caused by the ambient temperature around the spool material and (2) thermal damage caused by the coil wire.

[0083] (1) Specifically, the thermal damage caused by the ambient temperature around the aforementioned bobbin material is due to the rise in ambient temperature of the oil in the oil circulation path 3 using the oil check valve 40. In the oil check valve 40, the bobbin material is disposed close to the oil in the oil circulation path 3, so the ambient temperature around the bobbin material rises to near the oil temperature. The ambient temperature around the bobbin material at that temperature causes thermal degradation of the bobbin material.

[0084] The total amount of thermal damage to the bobbin material caused by the ambient temperature (hereinafter referred to as "total thermal damage") can be quantified based on the frequency of each oil temperature in the oil circulation path 3 during the period from the start time of use of the oil check valve 40 to the reference time for thermal damage determination.

[0085] Figure 4 This is a diagram illustrating an example of oil temperature history data D2 for oil circulation path 3. It should be noted that oil temperature history data D2 is actually time-series temperature data continuously acquired from oil temperature sensor 50. Figure 4 The figure shows the frequency of each oil temperature during the period from the start time of use of oil check valve 40 (e.g., when vehicle C is delivered) to the current time.

[0086] like Figure 4 As shown, the ECU100 of this embodiment continuously acquires time-series temperature data (oil temperature history data D2) from the oil temperature sensor 50, calculates the frequency of each oil temperature in the oil circulation path 3, and thereby derives the total amount of thermal damage to the spool material caused by the ambient temperature.

[0087] Here, the rate of thermal degradation of a component generally depends on the ambient temperature of the component. This rate of thermal degradation can be derived using the Arrhenius equation. From this perspective, in order to more accurately calculate the total thermal damage suffered by the spool material due to ambient temperature, the ECU100 of this embodiment uses the Arrhenius equation to convert oil temperature into a "b. heat coefficient," calculates the heat absorbed at each oil temperature (i.e., the amount of thermal damage) by calculating the product (a×b) with the "a. frequency" of that oil temperature, and sums these values ​​to derive the total amount of thermal damage as the total amount of heat absorbed. This total amount of thermal damage is then used as an explanatory variable input into the recognizer model described later. It should be noted that in this embodiment, the conversion of oil temperature into a "b. heat coefficient" using the Arrhenius equation is specifically for the polyamide resin used as the spool material of the oil check valve 40.

[0088] (2) The aforementioned thermal damage caused by the coil wire is due to the heat generated by the electromagnetic coil wound and fixed on the spool material of the oil check valve 40. The oil check valve 40 operates each time the flow path of the oil circulation path 3 is switched. The electromagnetic coil in the oil check valve 40 heats up each time due to the current flowing through it. The heat generated by the electromagnetic coil directly heats the spool material, thus causing thermal damage to the spool material.

[0089] Therefore, the degree of thermal damage to the spool material depends on the heating time of the electromagnetic coil, which in turn depends on the operating time of the oil check valve 40. Furthermore, the heating degree of the electromagnetic coil is greatest when switching from the OFF state to the ON state, and therefore it is also related to the number of times the oil check valve 40 operates.

[0090] That is, the total amount of thermal damage to the spool material caused by the heating of the coil can be quantified based on the total working time and total number of operations of the oil check valve 40 from the start time of its use to the reference time for thermal damage determination.

[0091] Figure 5 This is a diagram showing an example of the operating history data D3 of the oil check valve 40. It should be noted that the operating history data D3 is time-series data related to the ON / OFF state of the oil check valve 40. It should also be noted that the oil check valve 40 of this embodiment is set to the ON state when the fuel injector is OFF (e.g., at idle speed) and set to the OFF state when the fuel injector is injecting fuel (e.g., when the vehicle is moving).

[0092] like Figure 5 As shown, the ECU 100 of this embodiment calculates the total operating time and total number of operations from the start time of use of the oil check valve 40 (e.g., when vehicle C is delivered) to the current time based on time series data related to the ON / OFF state of the oil check valve 40, and uses this value as a reference for the total amount of thermal damage to the spool material caused by the coil wire. That is, the ECU 100 of this embodiment uses the operating frequency (total operating time and total number of operations) of the oil check valve 40 as an explanatory variable input into the recognizer model described later.

[0093] Figure 6 This graph shows the results of a market survey on the correlation between various parameters and the replacement / non-replacement status of oil check valves in vehicles. The survey confirmed the degree to which replacement and non-replacement vehicles could be distinguished under various parameters. It should be noted that... Figure 6 In each graph, two variables were selected from each parameter to confirm the correlation between the magnitude of each parameter and the vehicle with the oil check valve replaced / not replaced. Figure 6The "damage / mileage" is the value obtained by dividing the total thermal damage caused by ambient temperature by the total distance traveled.

[0094] from Figure 6 It can be seen that there is a strong correlation between the total thermal damage caused by ambient temperature, the total working time and total number of operations of the oil check valve, and whether the oil check valve was replaced or not (i.e., whether the malfunction occurred or not).

[0095] In addition, from Figure 6 It can be seen that the total driving distance of the vehicle is also strongly correlated with whether the oil check valve is replaced or not (i.e., whether the malfunction occurs or not).

[0096] Furthermore, the inventors of this invention have discovered that, as a further necessary condition, the type of vehicle, particularly the type of loading equipment the vehicle possesses, is strongly correlated with the frequency of replacement or non-replacement of the oil check valve (i.e., whether a malfunction occurs or not).

[0097] Figure 7 This graph represents the results of a market survey on the frequency of vehicle loading equipment categories and the replacement or non-replacement of oil check valves (i.e., whether a malfunction occurred or not). It should be noted that... Figure 7 The replacement ratio indicates the percentage of oil check valves in various vehicles that have been replaced or not replaced after a specified period of time (in this case, after 3.5 years) from the start of their use.

[0098] from Figure 7 It is known that in vehicles such as garbage trucks (i.e., garbage collection trucks) that frequently stop and start, the oil check valve deteriorates relatively quickly. This is because, in these vehicles, the engine is prone to overheating due to frequent stopping and starting, and the oil temperature in the oil circulation circuit 3 is also prone to high temperatures. Moreover, this is because, in these vehicles, the coil of the oil check valve also generates a greater degree of heat due to frequent stopping and starting.

[0099] Furthermore, market research indicates that the timing for replacing the oil check valve varies depending on the vehicle type. For example, refrigerated trucks, due to their operation, do not allow oil to leak externally; therefore, the oil check valve is replaced earlier, before oil leakage is detected, even if its appearance shows signs of deterioration. In other words, it is important to differentiate based on vehicle type when predicting and notifying users of the necessary oil check valve replacement.

[0100] It should be noted that the categories of loading equipment mounted on vehicles include, for example, garbage trucks, refrigerated trucks, concrete mixer trucks, concrete work trucks, oil tankers, sweepers, and convertibles.

[0101] As stated above, the replacement period of the oil check valve 40 largely depends on (1) the total thermal damage to the oil check valve 40 caused by the ambient temperature surrounding the spool material and (2) the total thermal damage to the oil check valve 40 caused by the coil wire. That is, by using these information as explanatory variables and constructing a machine learning-based recognizer model based on teacher data obtained in the market, the replacement period of the oil check valve 40 can be predicted.

[0102] Additionally, it is suggested that the prediction accuracy can be further improved by adding the total travel distance of vehicle C from the start time of use of oil check valve 40 and the type of loading equipment mounted on vehicle C as explanatory variables.

[0103] It should be noted that, considering the total thermal damage to the spool material, there is some overlap between the total thermal damage caused by the ambient temperature surrounding the spool material, the total thermal damage caused by the heating of the coil wire, and the total travel distance of vehicle C. However, in the machine learning-based recognizer model, these factors can be treated as separate features. Furthermore, during the learning process, the recognizer model can adjust the degree to which these factors influence the final necessity of replacing the oil check valve (i.e., the probability of the adverse event occurring).

[0104] In this embodiment, a neural network capable of handling large amounts of data and adept at nonlinear classification problems is used as the recognizer model D1.

[0105] Figure 8 This is a diagram illustrating an example of the structure of the recognizer model D1.

[0106] In order to predict when the oil check valve 40 needs to be replaced (e.g., the time when the oil check valve 40 malfunctions), the identifier model D1 of this embodiment calculates the probability of the oil check valve 40 malfunction occurring at a predetermined judgment reference time point based on the above factors.

[0107] Specifically, the identifier model D1 of this embodiment uses (a) the total driving distance of vehicle C, (b) the total operating time of oil check valve 40, (c) the total number of times oil check valve 40 operates, (d) the total thermal damage caused by the ambient temperature of the oil in the oil circulation path 3 due to oil temperature, and (e) the loading equipment category of vehicle C as explanatory variables. That is, the identifier model of this embodiment has input elements in the input layer for inputting these items. It should be noted that, among the elements (a) to (d), the total value from the start time of use of oil check valve 40 to the determination reference time is the input value.

[0108] Furthermore, the identifier model D1 of this embodiment has an output element in the output layer, which outputs the probability of a defect occurring at a predetermined judgment reference time point starting from the start time of use of the oil check valve 40. That is, the identifier model D1 of this embodiment outputs the probability of a defect occurring at a predetermined judgment reference time point as an indicator related to the replacement period of the oil check valve.

[0109] It should be noted that in the recognizer model D1 of this embodiment, the number of intermediate layers is set to 1 to reduce computational load. Furthermore, the ReLU function is used as the activation function for the intermediate layer, and the sigmoid function is used as the activation function for the output layer.

[0110] The recognizer model D1 underwent pre-processing based on teacher data collected in the market. It should be noted that the teacher data is a dataset that correlates the historical data (a) to (e) stored in the storage units of each vehicle with correct data related to whether or not the oil check valve of that vehicle has been replaced. It should also be noted that the teacher data used was obtained through undersampling, with a ratio of 1:1 between defective and healthy vehicles. Here, defective vehicles are defined as vehicles whose oil check valves have been replaced.

[0111] In the learning process, the input layer takes the resume data (a) to (e) as teacher data, and the output layer outputs whether the vehicle is healthy or in poor condition. Then, based on this result, whether the teaching is correct or incorrect, the network parameters (i.e., weighting coefficients and biases) are updated. Specifically, for example, the error between the correct (here, 1 or 0) value and the output value (i.e., the loss function) is taken, and the error is propagated from the output layer to each layer using backpropagation, adjusting the network parameters (i.e., weighting coefficients and biases) to approximate the correct value.

[0112] The external storage device 104 of vehicle C stores data of a learned recognizer model D1 that has undergone learning processing. That is, the external storage device 104 stores model data related to the input layer, intermediate layer and output layer of the neural network, as well as network parameters (i.e., weighting coefficients and biases) adjusted through learning processing.

[0113] <Specific handling for predicting the replacement period of oil check valves>

[0114] Next, the specific process for predicting the replacement period of the oil check valve 40 in the ECU100 of this embodiment will be explained.

[0115] Figure 9 This is a flowchart illustrating an example of the operation of ECU100. Figure 10 It is an illustrative explanationFigure 9 The flowchart is shown.

[0116] Figure 9 The basic concepts of the flowchart are as follows.

[0117] In this embodiment, the ECU 100 estimates the total thermal damage to the oil check valve 40 caused by the rise in ambient temperature due to the oil temperature, from the start time of use of the oil check valve 40 to a future judgment reference time (the reference time for determining the probability of malfunction of the oil check valve 40, hereinafter the same), based on the oil temperature history data D2 of the oil in the oil circulation path 3. Additionally, the ECU 100 estimates the operating frequency (i.e., the total thermal damage) of the oil check valve 40 from the start time of use of the oil check valve 40 to a future judgment reference time, based on the operating history data D3 of the oil check valve 40. Furthermore, the ECU 100 estimates the total driving distance of vehicle C from the start time of use of the oil check valve 40 to a future judgment reference time, based on the driving history data D4 of vehicle C.

[0118] For example, such as Figure 10 As shown, this estimation calculation is performed using the ratio of the time from the start time of use of the oil check valve 40 to the current time to the time from the start time of use of the oil check valve 40 to the future determination reference time (here, the ratio of the total travel distance). For example, the ECU 100 estimates each total value by increasing the ratio of the total values ​​from the start time of use of the oil check valve 40 to the current time, and uses this as the total value from the start time of use of the oil check valve 40 to the future determination reference time.

[0119] exist Figure 10 The diagram shows an example of the estimated values ​​for a future time point (hereinafter referred to as the "+30,000 km time point") where the total distance traveled by vehicle C at the current time point is 100,000 km. Here, in order to make the estimated values ​​for the +30,000 km time point correspond to the ratio of the total distance traveled, the estimated values ​​for the +30,000 km time point are calculated by multiplying the values ​​represented by the current time point's history by 1.3 times (=130,000 km / 100,000 km). Figure 10 For example, the total number of times the oil check valve 40 operates at +30,000 km is estimated to be 1,300 (1,000 times × 1.3), the total operating time of the oil check valve 40 at +30,000 km is estimated to be 6,500 hours (5,000 hours × 1.3), and the total thermal damage due to oil temperature at +30,000 km is estimated to be 130,000 (100,000 × 1.3).

[0120] Then, based on these factors, ECU100 uses the learned recognizer model D1 to calculate the probability of a malfunction occurring in the oil check valve 40 at a future judgment reference time point.

[0121] Furthermore, the ECU 100 calculates the probability of adverse events occurring at each time point in a manner that allows for the evolution of future judgment reference time points, and indicates the time point when the probability of adverse events occurring exceeds a predetermined value (in this case, 50%) as the period when the oil check valve 40 needs to be replaced. It should be noted that in this embodiment, the total travel distance of the vehicle C is used as the reference time point.

[0122] The following is a detailed explanation. Figure 9 The flowchart.

[0123] In step S1, ECU100 obtains the total driving distance of vehicle C based on the driving history data D4 stored in external storage device 104, and sets it as the input value of the recognizer model D1.

[0124] It should be noted that in step S1, the total driving distance of vehicle C, which is set as the input value of the recognizer model D1, is the total driving distance of vehicle C from the start time of use of oil check valve 40 to the future judgment reference time. However, in the initial loop processing, the total driving distance of vehicle C is temporarily set from the start time of use of oil check valve 40 to the current time.

[0125] In step S2, the ECU100 obtains the total number of operations and the total operating time of the oil check valve 40 based on the operating history data D3 of the oil check valve 40 stored in the external storage device 104, and sets it as the input value of the recognizer model D1. It should be noted that at this time, if referring to... Figure 5 As explained, ECU100 obtains the total working time and total number of operations from the start time of use of oil check valve 40 (e.g., when vehicle C is delivered) to the current time based on time series data (work history data D3) related to the ON / OFF of oil check valve 40.

[0126] It should be noted that in step S2, the total number of operations and total working time of the oil check valve 40, which are set as the input values ​​of the recognizer model D1, are the total number of operations and total working time of the oil check valve 40 from the start time of use of the oil check valve 40 to the future judgment reference time. However, in the initial loop processing, the total number of operations and total working time of the oil check valve 40 are temporarily set from the start time of use of the oil check valve 40 to the current time.

[0127] In step S3, the ECU100 obtains the total thermal damage to the oil check valve 40 caused by the oil temperature (ambient temperature) of the oil in the oil circulation path 3 based on the oil temperature history data D2 stored in the external storage device 104, and sets it as the input value of the identifier model D1. It should be noted that at this time, if referring to... Figure 4 As explained, the ECU100 calculates the frequency of each oil temperature in the oil circulation path 3 based on the time-series temperature data (oil temperature history data D2) continuously acquired from the oil temperature sensor 50. Then, the ECU100 calculates the thermal damage amount for each oil temperature by calculating the product (a×b) of "a. frequency" and "b. heat coefficient" obtained from the oil temperature using the Arrhenius formula, and sums these values ​​to calculate the total thermal damage amount for the oil check valve 40.

[0128] It should be noted that in step S3, the total thermal damage caused by the oil temperature (ambient temperature) of the oil circulation path 3, which is set as the input value of the identifier model D1, is the total thermal damage caused by the oil temperature (ambient temperature) of the oil circulation path 3 from the start time of use of the oil check valve 40 to the future judgment reference time. However, in the first cycle processing, the total thermal damage caused by the oil temperature (ambient temperature) of the oil circulation path 3 from the start time of use of the oil check valve 40 to the current time is temporarily set.

[0129] In step S4, ECU100 obtains the loading equipment category of vehicle C and sets it as the input value of the learned recognizer model D1. It should be noted that, here, the loading equipment category of vehicle C is selected and input by the user, for example, as one of the following: garbage truck, refrigerated truck, concrete mixer truck, concrete work truck, tanker truck, sweeper truck, and convertible truck.

[0130] In step S5, the ECU 100, based on the input values ​​set in steps S1 to S4, uses the learned recognizer model D1 to calculate the probability of a malfunction occurring in the oil check valve 40 at the reference time point (however, the current time point in the first loop). Specifically, the ECU 100 calculates the probability of a malfunction occurring in the oil check valve 40 through forward propagation processing of the learned recognizer model D1, based on the input values ​​set in steps S1 to S4.

[0131] In step S6, ECU100 determines whether the probability of a malfunction in oil check valve 40 is greater than or equal to a threshold (e.g., 50%). If the probability of a malfunction in oil check valve 40 is less than the threshold (S6: No), ECU100 proceeds to step S7.

[0132] In step S7, ECU100 adds a specified distance (here +30,000 km) to the total driving distance of vehicle C, thereby updating the data of the input value of the learner model D1 set in steps S1 to S3.

[0133] In step S7, as referred to Figure 10 As explained, ECU100 adds +30,000 km to the total driving distance of vehicle C, and calculates the total number of times the oil check valve 40 operates at +30,000 km, the total operating time of the oil check valve 40 at +30,000 km, and the total thermal damage due to oil temperature at +30,000 km.

[0134] After step S7, ECU100 returns to S1 and sets the calculated values ​​of these +30,000 km time points as the input values ​​of the learned recognizer model D1 (S1, S2, S3). Then, in step S5, ECU100 recalculates the probability of failure of oil check valve 40, and in S6, determines whether the probability of failure is above a threshold (e.g., 50%).

[0135] Thus, ECU100 repeatedly performs the cyclical processing of steps S1 to S7 (i.e., repeatedly adding 30,000 km to the total driving distance of vehicle C) until the probability of a malfunction in the oil check valve 40 reaches or exceeds a threshold. Then, when the probability of a malfunction reaches or exceeds the threshold (e.g., 50%) in step S6 (S6: Yes), ECU100 causes the processing to proceed to step S8.

[0136] In step S8, the ECU100 displays the time point when the probability of the oil check valve 40 malfunctioning reaches or exceeds a threshold (here, the total driving distance of the vehicle C when the probability of the oil check valve 40 malfunctioning reaches or exceeds the threshold) on the display unit 107 as the time when the oil check valve 40 needs to be replaced.

[0137] Figure 11 This is a diagram showing an example of a display screen displayed on the display unit 107 of the ECU 100.

[0138] The display screen of this embodiment includes: an input receiving unit m1, which accepts the user's selection input for the loading equipment type of vehicle C; an input receiving unit m2, which accepts the selection input of data read from the external storage device 104 (i.e., history data D2, D3, D4); and an input receiving unit m3, which accepts the input of the total driving distance when the oil check valve 40 was last replaced.

[0139] Furthermore, when the user inputs these items and selects the "Start Analysis Execution" button (m4) on the display screen, ECU100 executes... Figure 9The flowchart processing. Then, ECU100 will pass through Figure 9 The replacement period of the oil check valve 40, calculated from the flowchart, is displayed in the analysis results display area m5 on the screen.

[0140] [Effect]

[0141] As described above, the predictive device for predicting the replacement period of the oil check valve in this embodiment includes:

[0142] The acquisition unit acquires first information and second information from the storage unit. The first information is information related to the operational history of the oil check valve, and the second information is information related to the oil temperature history of the oil in the oil circulation path.

[0143] The computing unit, based on the first information and the second information, uses a pre-learned recognizer model to calculate an index related to the required replacement period of the oil check valve.

[0144] According to the predictive device of this embodiment, it is possible to suggest in advance when the oil check valve needs to be replaced. Therefore, component replacement can be performed before the oil check valve fails, thus preventing sudden failures of the oil check valve.

[0145] Furthermore, especially in the prediction device of this embodiment, the replacement period of the oil check valve can be predicted by using a simple recognizer model based on a neural network. This is also advantageous in that the prediction calculation can be performed without computational load.

[0146] (Variation Example 1)

[0147] The above embodiment shows a method in which the time point (total driving distance of vehicle C) at which the probability of failure of oil check valve 40 is above the threshold is displayed as the time when oil check valve 40 needs to be replaced. However, it is sometimes convenient for users to know the progression of the probability of failure of oil check valve 40 in future periods.

[0148] From this perspective, the ECU 100 can also display on the display unit 107 the shift in the probability of malfunction of the oil check valve 40 in future periods. For example, the ECU 100 displays the shift in the probability of malfunction of the oil check valve 40 corresponding to the elapsed time from the current time point.

[0149] Figure 12 This is an example of a display showing the progression of the probability of an adverse event occurring. It should be noted that, when implementing this variation, it is preferable to... Figure 9In step S7 of the flowchart, the total travel distance added to the total travel distance of vehicle C is set to a shorter value. This reduces the interval between plotted points that decreases the probability of malfunctions of the oil check valve 40 in future periods.

[0150] (Variation Example 2)

[0151] The above embodiment illustrates a neural network as an example of the recognizer model D1, but other models can also be used as the recognizer model D1. For example, as the recognizer model D1, an SVM (Support Vector Machine) or a Bayesian classifier can be used, or an ensemble model can be used. Alternatively, multiple types of recognizers can be combined to form the model.

[0152] (Variation Example 3)

[0153] In the above embodiment, when estimating the total thermal damage to the oil check valve 40 caused by the rise in ambient temperature due to the oil temperature from the start time of use of the oil check valve 40 to a future judgment reference time based on the oil temperature history data D2 of the oil in the oil circulation path 3, the ratio of the time from the start time of use of the oil check valve 40 to the current time to the time from the start time of use of the oil check valve 40 to the future judgment reference time (in the above, the ratio of the total driving distance) is used. However, this estimation calculation can be adjusted in various ways. For example, if the frequency of use of vehicle C or the frequency of oil temperature varies seasonally, a calculation formula that takes into account this variation can also be used.

[0154] The specific examples of the present invention have been described in detail above, but these are merely illustrative and do not limit the scope of the claims. The technology described in the claims includes various modifications and alterations to the specific examples illustrated above.

[0155] Industrial applicability

[0156] According to the predictive device of the present invention, it is possible to predict when the oil check valve installed in a vehicle needs to be replaced.

Claims

1. A prediction device that predicts a required replacement timing of an oil check valve provided to an oil circulation passage of a vehicle, the prediction device characterized by comprising: an acquisition section that acquires first information and second information from a storage section, the first information being information related to an operation history of the oil check valve, the second information being information related to an oil temperature history of oil in the oil circulation passage; and an arithmetic section that calculates an index related to the required replacement timing of the oil check valve, using a learned recognizer model, based on the first information and the second information.

2. The prediction device according to claim 1, wherein the arithmetic section estimates, based on the first information, an operation frequency of the oil check valve from a start time point of use of the oil check valve to a prescribed time point in the future, and estimates, based on the second information, an oil temperature frequency of the oil from the start time point of use of the oil check valve to the prescribed time point in the future, and calculates the index at the prescribed time point in the future by inputting these values to the learned recognizer model.

3. The prediction device according to claim 2, wherein the arithmetic section calculates the index at each time point in the future in a manner that time evolves the prescribed time point in the future, and presents a time point at which the index exceeds a prescribed value as the required replacement timing of the oil check valve.

4. The prediction device according to claim 1, wherein the acquisition section further acquires third information related to a loading device category of the vehicle, the arithmetic section calculates the index, using the learned recognizer model, based on the first information, the second information, and the third information.

5. The prediction device according to claim 1, wherein the acquisition section further acquires fourth information related to a travel history of the vehicle from the storage section, the arithmetic section calculates the index, using the learned recognizer model, based on the first information, the second information, and the fourth information.

6. The prediction device according to claim 1, wherein the first information includes information related to a total number of operations and a total operation time of the oil check valve.

7. The prediction device according to claim 1, wherein the second information includes information related to a frequency of each oil temperature of the oil.

8. The prediction device according to claim 7, wherein the oil temperature is converted into a heating degree coefficient of a bobbin material in the oil check valve depending on the oil temperature using an Arrhenius formula, the oil temperature history is referred to as information indicating a total thermal damage amount of the bobbin material, the total thermal damage amount being calculated based on the frequency of each oil temperature and the heating degree coefficient.

9. The prediction device according to claim 1, wherein the learned recognizer model is constituted by a neural network.

10. The prediction device according to claim 1, wherein the index is a probability of occurrence of a failure of the oil check valve.

11. The prediction device according to claim 1, wherein ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ ​ The operation section displays the progress of the index of the oil check valve corresponding to the elapsed time from the current time point.

12. A prediction method of predicting a required replacement timing of an oil check valve provided in an oil circulation passage of a vehicle, the prediction method characterized by, The processing includes: processing of acquiring first information and second information from a storage section, the first information being information related to an operation history of the oil check valve, and the second information being information related to an oil temperature history of oil in the oil circulation path; and processing of calculating an index related to the replacement required period of the oil check valve, based on the first information and the second information, using a recognizer model that has been learned in advance.

13. A computer-readable storage medium having stored thereon a prediction program of predicting a replacement required period of an oil check valve provided in an oil circulation path of a vehicle, wherein the prediction program, when executed by a processor, implements the following processing: processing of acquiring first information and second information from a storage section, the first information being information related to an operation history of the oil check valve, and the second information being information related to an oil temperature history of oil in the oil circulation path; and processing of calculating an index related to the replacement required period of the oil check valve, based on the first information and the second information, using a recognizer model that has been learned in advance. ​

Images