Wheel nut loosening prediction device, wheel nut loosening prediction method, computational model generation system, and vehicle operation system

Abstract

To provide a wheel nut looseness prediction device, a wheel nut looseness prediction method, a calculation model generation system and a vehicle operation system, capable of properly predicting looseness of a wheel nut at a low cost.SOLUTION: A wheel nut looseness prediction device 10 includes a vehicle information acquisition unit 12 and a wheel nut looseness calculation unit 13. The vehicle information acquisition unit 12 acquires vehicle information including a travel distance of a vehicle, and a temperature and an air pressure of a tire 5 mounted on the vehicle. The wheel nut looseness calculation unit 13 has a calculation model 13b for predicting looseness of a wheel nut 50 of the tire 5 on the basis of input data, and predicts the looseness of the wheel nut 50 by inputting the vehicle information acquired by the vehicle information acquisition unit 12 to the calculation model 13b.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a wheel nut loosening prediction device, a wheel nut loosening prediction method, a computational model generation system, and a vehicle operation system that predict loosening of wheel nuts on tires mounted on a vehicle. [Background technology]

[0002] Tires mounted on vehicles are fastened to the axle by a number of wheel nuts, for example, at the wheel portion. The fastening force of the wheel nuts can decrease due to initial break-in after tightening, and so they must be retightened after a certain period of vehicle driving.

[0003] Patent Document 1 describes a technique for detecting wheels with loose wheel nuts. This technique utilizes a wheel speed signal to detect wheel abnormalities such as loose wheels. The wheel speed signal is used as a basis for determining a first detection signal and a second detection signal. First and second reference signals are also used to determine the first and second detection signals, respectively. If at least one of the first and second detection signals exceeds a threshold, an abnormality, such as a loose wheel, is detected. [Prior art documents] [Patent documents]

[0004] [Patent Document 1] Special Publication No. 2018-506470 Summary of the Invention [Problem to be solved by the invention]

[0005] The conventional detection technology described in Patent Document 1 requires a wheel speed sensor that measures wheel speed to detect wheels with loose wheel nuts. Furthermore, the conventional detection technology uses a defect signal in the measured wheel speed to determine looseness, which means that the looseness determination can be affected by factors such as mechanical behavior and road surface conditions that vary from vehicle to vehicle.

[0006] The present invention has been made in consideration of the above circumstances, and its purpose is to provide a wheel nut loosening prediction device, a wheel nut loosening prediction method, a computational model generation system, and a vehicle operation system that can inexpensively and appropriately predict wheel nut loosening. [Means for solving the problem]

[0007] A wheel nut loosening prediction device according to one embodiment of the present invention comprises a vehicle information acquisition unit that acquires vehicle information including the vehicle's mileage and the temperature and air pressure of tires mounted on the vehicle, and a wheel nut loosening calculation unit that has a calculation model that predicts loosening of wheel nuts of the tires based on input data and inputs the vehicle information acquired by the vehicle information acquisition unit into the calculation model to predict loosening of the wheel nuts.

[0008] Another aspect of the present invention is a method for predicting loosening of wheel nuts, which includes a vehicle information acquisition step of acquiring vehicle information including a vehicle mileage and the temperature and air pressure of tires mounted on the vehicle, and a wheel nut looseness calculation step of predicting loosening of the wheel nuts by inputting the vehicle information acquired in the vehicle information acquisition step into a computational model that predicts loosening of wheel nuts of the tires based on input data.

[0009] Another aspect of the present invention is a computational model generation system that includes a vehicle information acquisition unit that acquires vehicle information including a vehicle mileage and the temperature and air pressure of tires mounted on the vehicle, a wheel nut loosening calculation unit that has a computational model that predicts loosening of wheel nuts of the tires based on input data and inputs the vehicle information acquired by the vehicle information acquisition unit into the computational model to predict loosening of the wheel nuts, and a learning processing unit that compares the looseness of the wheel nuts calculated by the wheel nut loosening calculation unit with a change in an indicator that indicates looseness of the wheel nuts to train the computational model.

[0010] Another aspect of the present invention is a vehicle operation system that includes the wheel nut loosening prediction device described above, an operation plan management device that manages operation plans for the vehicle, and a work plan management device that manages maintenance work plans that include retightening of the loosened wheel nuts, and when loosening of the wheel nuts is predicted by the wheel nut loosening prediction device, the operation plan management device presents a plan proposal for adding retightening work to the operation plan presented by the work plan management device during free time in the work plan. [Effects of the Invention]

[0011] According to the present invention, loosening of wheel nuts can be predicted inexpensively and appropriately. [Brief explanation of the drawings]

[0012] [Figure 1] 1 is a block diagram showing the functional configuration of a wheel nut loosening prediction device according to a first embodiment. FIG. [Figure 2] FIG. 2 is a block diagram showing the functional configuration of the on-board measuring device. [Figure 3] FIG. 10 is a schematic diagram for explaining calculation and learning in a computation model. [Figure 4] FIG. 1 is a block diagram showing a functional configuration of a computation model generation system. [Figure 5] FIG. 2 is a side view of a portion of a tire including a wheel nut. [Figure 6] 1 is a flowchart showing a procedure for generating a computation model by the computation model generation system. [Figure 7] FIG. 10 is a block diagram showing the functional configuration of a vehicle operation system according to a second embodiment. DETAILED DESCRIPTION OF THE INVENTION

[0013] The present invention will be described below based on preferred embodiments with reference to Figures 1 to 7. The same or equivalent components and members shown in each drawing are designated by the same reference numerals, and duplicate descriptions will be omitted where appropriate. The dimensions of the members in each drawing are enlarged or reduced as appropriate for ease of understanding. Some members that are not important for explaining the embodiments will be omitted from the drawings.

[0014] (Embodiment 1) 1 is a block diagram showing the functional configuration of a wheel nut loosening prediction device 10 according to embodiment 1. The wheel nut loosening prediction device 10 is connected to an on-board measurement device 70, a weather information server device 80, and the like mounted on a vehicle via a communication network 9, and acquires vehicle information, weather information, and the like. Based on the acquired vehicle information, weather information, and the like, the wheel nut loosening prediction device 10 predicts loosening of a wheel nut 50 using a calculation model 13b.

[0015] The wheel nut loosening prediction device 10 acquires vehicle information from an on-board measurement device 70 mounted on the vehicle via a communication network 9 such as the Internet. The vehicle information includes vehicle measurement information such as the vehicle's speed, acceleration, load, and position information, as well as tire measurement information measured on the tires 5. The wheel nut loosening prediction device 10 also acquires weather information from a weather information server device 80.

[0016] The calculation model 13b of the wheel nut loosening prediction device 10 is trained using the looseness measured by an indicator attached to the wheel nut 50 as training data, and outputs, for example, the probability that the wheel nut 50 is loose. A scale may be defined to evaluate the looseness of the wheel nut 50 in multiple stages, ranging from "not loose" to "loose," and the calculation model 13b may output the evaluation result for the looseness of the wheel nut 50.

[0017] 2 is a block diagram showing the functional configuration of the on-vehicle measurement device 70. The on-vehicle measurement device 70 includes a vehicle measurement unit 71, a tire measurement unit 72, an information acquisition unit 73, and a communication unit 74. Each unit in the on-vehicle measurement device 70 can be realized in terms of hardware using electronic elements and mechanical parts, such as a computer CPU, and in terms of software using a computer program, but the functional blocks shown here are realized by the cooperation of these elements. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

[0018] The vehicle measurement unit 71 has a speedometer 71a, a GPS receiver 71b, an acceleration sensor 71c, and the like, which are mounted on the vehicle. The speedometer 71a measures the speed of the vehicle. The GPS receiver 71b measures the current position information (latitude, longitude, and altitude) of the vehicle. The acceleration sensor 71c measures the acceleration of the vehicle in three axial directions. The vehicle measurement unit 71 may also have a weighing scale (not shown) to measure the load of cargo carried on the vehicle. Note that, when the load of cargo carried on the vehicle is obtained in advance as known information, the known information may be acquired and used by the wheel nut loosening prediction device 10.

[0019] The tire measurement unit 72 has a temperature sensor 72a and a pressure sensor 72b. The temperature sensor 72a and the pressure sensor 72b are disposed on an air valve or the like of a tire 5 mounted on a vehicle, or are firmly wrapped around and fixed to a wheel with a belt or the like, and measure the temperature and air pressure of the tire 5. The temperature sensor 72a may be disposed on an inner liner or the like of the tire 5. Note that an acceleration sensor separate from the acceleration sensor 71c mounted on the vehicle may be disposed on the inner liner or the like of the tire 5.

[0020] The information acquisition unit 73 acquires vehicle measurement information (speed, position information, acceleration, etc.) measured by the vehicle measurement unit 71, tire measurement information (tire temperature, air pressure, etc.) measured by the tire measurement unit 72, and tire identification information (described later), etc. The information acquisition unit 73 associates measurement time information or acquired time information with each measurement data included in the vehicle measurement information and tire measurement information. The information acquisition unit 73 transmits the vehicle measurement information and tire measurement information, together with the time information associated with each measurement data, from the communication unit 74 to the wheel nut loosening prediction device 10.

[0021] If the vehicle is equipped with an electronic control device or a device such as a digital tachometer, the information acquisition unit 73 may acquire information such as vehicle speed, acceleration, and position information collected by the device. The communication unit 74 connects to the communication network 9 by wireless communication such as WiFi (registered trademark), and transmits the vehicle measurement information, tire measurement information, and time information acquired by the information acquisition unit 73 to the wheel nut loosening prediction device 10 via the communication network 9.

[0022] Returning to Figure 1, the weather information server device 80 provides weather information for various locations. The weather information provided by the weather information server device 80 includes information such as the amount of precipitation, snow accumulation, snowfall, temperature, and sunshine hours for various locations. The wheel nut loosening prediction device 10 obtains from the weather information server device 80 the weather information for the location where the vehicle is traveling.

[0023] The wheel nut loosening prediction device 10 comprises a communication unit 11, a vehicle information acquisition unit 12, a wheel nut loosening calculation unit 13, and a memory unit 14. Each unit in the wheel nut loosening prediction device 10 can be realized in hardware terms using electronic elements and mechanical parts such as a computer CPU, and in software terms using a computer program, etc., but the functional blocks realized by the cooperation of these are depicted here. Therefore, it will be understood by those skilled in the art that these functional blocks can be realized in various forms by combining hardware and software.

[0024] The communication unit 11 is connected to the communication network 9 by wireless or wired communication, and communicates with the communication unit 74 of the on-vehicle measuring device 70. The communication unit 11 also communicates with the weather information server device 80 via the communication network 9.

[0025] The vehicle information acquisition unit 12 acquires vehicle information including vehicle measurement information (speed, position information, acceleration, load, etc.) and tire measurement information (tire temperature, air pressure, etc.) transmitted from an on-board measurement device 70 mounted on the vehicle. The vehicle information acquisition unit 12 calculates and acquires the vehicle's traveling distance based on the vehicle measurement information.

[0026] The vehicle information acquisition unit 12 can calculate and acquire the travel distance based on the position information of the vehicle measurement information. The travel distance of the vehicle may also be calculated based on the speed data in the vehicle measurement information and the time data associated with that data. That is, the travel distance of the vehicle can be calculated by multiplying the speed data arranged in chronological order by the time difference until the next point in time. The speed of the vehicle may also be calculated from the travel distance of the vehicle based on the position information arranged in chronological order and the interval between acquisitions of the position information.

[0027] If information regarding the mileage of the vehicle is provided from the vehicle or an external device for vehicle management, the vehicle information acquisition unit 12 does not need to calculate the mileage itself and may acquire the information regarding the mileage from the vehicle or the external device. The vehicle information acquisition unit 12 may also acquire information regarding the load of cargo on the vehicle from an external device.

[0028] The vehicle information acquisition unit 12 outputs the acquired traveling distance to the wheel nut loosening calculation unit 13. The vehicle information acquisition unit 12 outputs the acquired tire measurement information (tire temperature, air pressure, etc.) to the wheel nut loosening calculation unit 13.

[0029] When the wheel nut loosening calculation unit 13 estimates the loosening of the wheel nuts 50 based on a calculation model that uses the acceleration of the vehicle as an input element, the vehicle information acquisition unit 12 outputs acceleration data in the vehicle measurement information to the wheel nut loosening calculation unit 13. The vehicle information acquisition unit 12 may also calculate the number of times the vehicle has turned based on position information, etc., and output the calculated number of times to the wheel nut loosening calculation unit 13.

[0030] Furthermore, the vehicle information acquisition unit 12 acquires data used to estimate the looseness of the wheel nuts 50 from the storage unit 14, among the vehicle specification data 14a, tire specification data 14b, and tire position data 14c, and outputs the data to the wheel nut looseness calculation unit 13. The storage unit 14 is a storage device configured, for example, with an SSD (Solid State Drive), a hard disk, a CD-ROM, a DVD, or the like, and stores data provided in advance regarding the specifications of various vehicles and tires 5.

[0031] The vehicle specification data 14a includes information on vehicle performance such as the manufacturer, vehicle name, vehicle model, vehicle weight, drive train, overall length, width, height, and maximum load capacity. The tire specification data 14b includes information on tire 5 performance such as the manufacturer, product name, tire size, tire width, aspect ratio, wear resistance, tire strength, static stiffness, dynamic stiffness, tire outer diameter, load index, and manufacturing date. The tire specification data 14b also includes information on the wheel, including the manufacturing date and type of aluminum or steel, and information on the wheel nuts 50, including thread specifications and material such as aluminum or steel.

[0032] The tire position data 14c also includes information about the tire's position on the vehicle, tire identification information, and information about the axle on which it is mounted. The tire identification information is a serial number, such as a manufacturing number, that is assigned to each tire to identify it. The tire identification information, tire placement position, and information about the axle may be stored in the storage unit 14 by an operator inputting the information, for example, when mounting the tire on the vehicle.

[0033] The wheel nut loosening calculation unit 13 includes a pre-processing unit 13a and a calculation model 13b. The pre-processing unit 13a aggregates data input from the vehicle information acquisition unit 12 and removes abnormal values. The vehicle information acquisition unit 12 acquires data from the vehicle for each journey from the departure point to the destination, and acquires and stores data every 10 seconds during the journey, for example.

[0034] The pre-processing unit 13a aggregates various data items into a single value, such as vehicle measurement information such as mileage, speed, acceleration, load, and number of turns, tire measurement information such as temperature and air pressure of the tires 5, and meteorological information such as air temperature and weather. The pre-processing unit 13a may aggregate data for each trip, or may aggregate data accumulated over a certain period (such as one week or one month).

[0035] For example, the pre-processing unit 13a calculates the total traveled distance by adding up the traveled distance data acquired during a period. Also, the pre-processing unit 13a calculates one average temperature data by averaging the temperature data during the vehicle operation for one day, for example.

[0036] The pre-processing unit 13a may extract the maximum value from the load data for one day of operation, or may extract the maximum value from the load data for all operations for one month. The pre-processing unit 13a may also calculate one average load data by averaging the maximum values ​​of the load data for all operations.

[0037] 3 is a schematic diagram for explaining calculation and learning in the calculation model 13b. Data input to the calculation model 13b is roughly classified into vehicle measurement information, tire measurement information, and other information.

[0038] Input data related to vehicle measurement information includes the vehicle speed, acceleration, mileage, and load. The mileage is acquired by the vehicle information acquisition unit 12 as described above. Input data related to tire measurement information includes the temperature and air pressure of the tire 5. Note that the vehicle acceleration is used as input data to the calculation model as appropriate.

[0039] The input data based on other information includes meteorological information such as temperature, weather, and road surface conditions estimated based on the meteorological information; the maximum vehicle load capacity included in the vehicle specification data 14a; and the age and wear resistance of the tire 5, information on the wheel nuts 50, and the like included in the tire specification data 14b. The age of the tire 5 is the number of years that have passed since the tire 5 was manufactured. The wear resistance of the tire 5 is measured using, for example, a tire wear index value that indexes the wear resistance of various tread compounds based on a Lambourn abrasion test, with a standard compound being 100. The input data based on other information also includes the position of the tire 5, tire identification information, and information on the axle included in the tire position data 14c.

[0040] The computational model 13b uses a learning model such as a neural network. The computational model 13b may also be constructed by a method such as logistic regression, support vector machine (SVM), linear regression, decision tree, or random forest. The computational model 13b is not limited to these, and may be any algorithm capable of supervised learning.

[0041] 4 is a block diagram showing the functional configuration of the computational model generation system 100. The computational model generation system 100 includes a wheel nut inspection device 60 and a computational model generation device 20 having a learning processing unit .

[0042] The wheel nut inspection device 60 is composed of a camera and the like that photographs the side of the tire 5, and inspects the wheel nuts 50 for looseness. Figure 5 is a side view of a portion of the tire 5, including the wheel nuts 50. The wheel nuts 50 are provided with indicators 51 for detecting looseness. When the wheel nuts 50 loosen and rotate, the position of the tip 51a of the indicator 51 shifts, indicating that the wheel nuts 50 have loosened.

[0043] The wheel nut inspection device 60 may perform image analysis of the captured image data to automatically detect the rotation of the indicator 51, or an operator may view the image and determine the rotation of the indicator 51. The wheel nut inspection device 60 outputs the looseness state of the wheel nut 50 based on whether or not the indicator 51 has rotated to the learning processing unit 21 of the computational model generation device 20.

[0044] The components of the wheel nut loosening prediction device 10 in the computational model generating device 20 have the same functions as those of the wheel nut loosening prediction device 10, but the computational model 13b is either before learning or is currently being learned.

[0045] The learning processing unit 21 uses the looseness state of the wheel nuts measured by the wheel nut inspection device 60 as training data and causes the calculation model 13b to learn. Referring to Figure 3, in the learning process of the calculation model 13b, the calculation model 13b calculates the looseness of the wheel nuts based on the input information and compares it with the training data. The learning processing unit 21 performs learning by newly setting various coefficients in the calculation process of the looseness of the wheel nuts 50 estimated by the calculation model 13b, and repeatedly updating the model.

[0046] The learning processing unit 21 can use a known learning method such as gradient boosting, and the computational model 13b can be verified using a known verification method such as random data sampling or cross-validation.

[0047] Next, the operation of the wheel nut loosening prediction device 10 and the computational model generation system 100 will be described. Fig. 6 is a flowchart showing the procedure for generating a computational model by the computational model generation system 100. The vehicle information acquisition unit 12 starts acquiring vehicle measurement information and tire measurement information (S1). In addition, in step S1, the vehicle information acquisition unit 12 of the computational model generation device 20 reads out necessary information such as vehicle specifications, tire specifications, and tire positions as other information from the storage unit 14. The vehicle information acquisition unit 12 starts calculating the mileage (S2).

[0048] The pre-processing unit 13a of the wheel nut loosening calculation unit 13 aggregates (S3) each piece of data input from the vehicle information acquisition unit 12 for the period during which the data was acquired. As described above, the pre-processing unit 13a calculates data such as the total mileage, average temperature, and average load.

[0049] The wheel nut loosening calculation unit 13 inputs the input data from the vehicle information acquisition unit 12 and the data aggregated by the pre-processing unit 13a to the calculation model 13b, and calculates and predicts the loosening of the wheel nuts 50 using the calculation model 13b (S4).

[0050] The learning processing unit 21 compares the looseness of the wheel nuts 50 predicted by the wheel nut looseness calculation unit 13 with the looseness state of the wheel nuts 50 as an inspection result by the wheel nut inspection device 60 (S5). The learning processing unit 21 updates the computation model 13b based on the comparison result in step S6 (S6) and ends the processing. By repeating these processes, the computation model generation device 20 updates the computation model 13b and improves the accuracy in predicting the looseness of the wheel nuts 50.

[0051] The wheel nut loosening prediction device 10 predicts loosening of the wheel nuts 50 by using the trained computation model 13b generated by the computation model generation device 20. The wheel nut loosening prediction device 10 predicts loosening of the wheel nuts 50 by executing the processes from step S1 to step S4 in the flowchart shown in FIG.

[0052] The wheel nut loosening prediction device 10 can inexpensively and appropriately predict loosening of the wheel nuts 50 by predicting loosening of the wheel nuts 50 using a computational model 13b that uses as input data vehicle information including the vehicle mileage and the temperature and air pressure of the tire 5. Furthermore, the computational model generation system 100 can use the looseness state of the wheel nuts 50, which is the inspection result by the wheel nut inspection device 60, as training data to generate a computational model 13b that inexpensively and appropriately predicts loosening of the wheel nuts 50.

[0053] Compared to conventional methods that make judgments based solely on the mileage since the wheel was attached, the wheel nut loosening prediction device 10 can predict loosening of wheel nuts 50 at the appropriate time. The wheel nut loosening prediction device 10 is able to predict loosening taking into account factors such as the vehicle's driving style using input data to the calculation model 13b. This makes it possible to determine, based on the looseness of the wheel nuts 50 predicted by the wheel nut loosening prediction device 10, whether retightening of the wheel nuts 50 needs to be completed earlier than the specified mileage, or conversely, whether retightening can be completed later than the specified mileage, thereby enabling efficient retightening maintenance to be performed in accordance with the vehicle's operating plan.

[0054] The wheel nut loosening prediction device 10 can construct a calculation model 13b that is adaptable to various wheel nuts 50 by inputting information about the wheel, including aluminum, steel, etc., and information about the wheel nut 50, including the thread standard and material, such as aluminum, steel, etc., into the calculation model 13b, thereby improving the accuracy of predicting loosening of the wheel nuts 50.

[0055] Strictly speaking, the wheel nut loosening prediction device 10 does not capture the moment when the indicator 51 shifts position and use that as training data to train the calculation model 13b. For this reason, it is thought that there is a certain degree of flexibility in the timing for predicting loosening of the wheel nuts 50. The wheel nut loosening prediction device 10 can provide the timing for preventative retightening of the wheel nuts 50 by using the output of the calculation model 13b as the probability that the wheel nuts 50 are rotating. For example, if the wheel nut loosening prediction device 10 predicts that the wheel nuts 50 are rotating at a rate of 70% or higher, the vehicle operations manager can create a vehicle maintenance plan for preventative retightening.

[0056] For example, the wheel nut inspection device 60 may be configured to erect support posts on both sides of the entrance / exit of the base of a transportation company that operates the vehicle, and use cameras mounted on the posts to capture images of the tire 5 from the left and right sides. For example, when the vehicle returns to the base and passes through the entrance / exit, the wheel nut inspection device 60 automatically captures images of the tire side, wheel, and individual wheel nuts 50 with the camera, creates image data corresponding to the mounting position of the vehicle and tire 5, and determines how far the indicator 51 has rotated from its initial position. For example, in a vehicle such as an autonomous truck, the wheel nut inspection device 60 may determine how far the indicator 51 has rotated from its initial position based on images of the tire side and individual wheel nuts 50 included in images captured by an on-board camera that captures the side of the vehicle. The computational model generation system 100 may compare the rotation angle of the indicator 51 determined by the wheel nut inspection device 60 with the predicted result of loosening of the wheel nuts 50 output by the computational model 13b and update the computational model 13b.

[0057] (Embodiment 2) 7 is a block diagram showing the functional configuration of a vehicle operation system 110 according to the second embodiment. The vehicle operation system 110 includes the wheel nut loosening prediction device 10 described in the first embodiment, an operation plan management device 31, and a work plan management device 32. The operation plan management device 31 manages plans for operating vehicles, such as an operation plan for the transportation of goods by trucks over several months at a transportation company. The operation plan management device 31 holds operation plan data for each vehicle, and reflects the schedule of new transportation requests, vehicle maintenance schedules, and the like in the operation plan data.

[0058] The work plan management device 32 manages work plans such as inspection and maintenance of vehicles of each transportation company at, for example, a maintenance company that performs maintenance work. Vehicle maintenance includes tightening the wheel nuts 50 of the vehicle. The work plan management device 32 holds work plan data such as inspection work and maintenance work for vehicles, and reflects the schedule of new work requests and the like in the work plan data.

[0059] The wheel nut loosening prediction device 10 provides the operation plan management device 31 and the work plan management device 32 with looseness information of the wheel nuts 50 predicted by the calculation model 13b. When the wheel nut loosening prediction device 10 predicts loosening of the wheel nuts 50, the operation plan management device 31 references the work plan data held by the work plan management device 32 and presents a proposed plan for adding retightening work of the wheel nuts 50 to the operation plan data for a free time in the work plan data. This allows the vehicle operation system 110 to provide a plan for appropriately performing retightening maintenance of the wheel nuts 50 in the vehicle operation plan, thereby increasing convenience for the operation planner.

[0060] Furthermore, when the wheel nut loosening prediction device 10 predicts loosening of the wheel nuts 50, the work plan management device 32 may provide the operation plan management device 31 with the free time in the work plan data it holds. The operation plan management device 31 compares the free time in the provided work plan data with the vehicle operation plan, and presents a plan proposal for adding retightening work of the wheel nuts 50 to the operation plan data, thereby improving convenience for the operation planner.

[0061] Furthermore, the vehicle operation system 110 manages whether the retightening work has been completed in accordance with the proposed plan. If the completion of the retightening work managed by the work plan management device 32 cannot be confirmed, the operation plan management device 31 may not incorporate the vehicle into an operation plan such as a new transportation request.

[0062] Next, features of the wheel nut loosening prediction device 10, the wheel nut loosening prediction method, the computational model generation system 100, and the vehicle operation system 110 according to each embodiment will be described. The wheel nut loosening prediction device 10 includes a vehicle information acquisition unit 12 and a wheel nut loosening calculation unit 13. The vehicle information acquisition unit 12 acquires vehicle information including the vehicle's mileage and the temperature and air pressure of the tires 5 mounted on the vehicle. The wheel nut loosening calculation unit 13 has a calculation model 13b that predicts loosening of the wheel nuts 50 of the tires 5 based on input data, and predicts loosening of the wheel nuts 50 by inputting the vehicle information acquired by the vehicle information acquisition unit 12 into the calculation model 13b. This allows the wheel nut loosening prediction device 10 to accurately predict loosening of the wheel nuts 50 at low cost.

[0063] The input data includes information about the wheel nuts 50, including thread specifications. This allows the wheel nut loosening prediction device 10 to construct a calculation model 13b that is adaptable to various wheel nuts 50, thereby improving the accuracy of predicting loosening of the wheel nuts 50.

[0064] The calculation model 13b also calculates the probability that the wheel nuts 50 are rotating. This enables the wheel nut loosening prediction device 10 to provide the timing for preventative retightening of the wheel nuts 50.

[0065] The wheel nut loosening prediction method includes a vehicle information acquisition step and a wheel nut loosening calculation step. The vehicle information acquisition step acquires vehicle information including the vehicle mileage and the temperature and air pressure of the tires 5 mounted on the vehicle. The wheel nut loosening calculation step predicts loosening of the wheel nuts 50 by inputting the vehicle information acquired in the vehicle information acquisition step into a calculation model 13b that predicts loosening of the wheel nuts 50 of the tires 5 based on input data. This wheel nut loosening prediction method makes it possible to inexpensively and appropriately predict loosening of the wheel nuts 50.

[0066] The computational model generation system 100 includes a vehicle information acquisition unit 12, a wheel nut loosening calculation unit 13, and a learning processing unit 21. The vehicle information acquisition unit 12 acquires vehicle information including the vehicle's mileage and the temperature and air pressure of the tires 5 mounted on the vehicle. The wheel nut loosening calculation unit 13 has a computational model 13b that predicts loosening of the wheel nuts 50 of the tires 5 based on input data, and inputs the vehicle information acquired by the vehicle information acquisition unit 12 into the computational model 13b to predict loosening of the wheel nuts 50. The learning processing unit 21 compares the looseness of the wheel nuts 50 calculated by the wheel nut loosening calculation unit 13 with changes in the indicators 51 that indicate looseness of the wheel nuts 50, and trains the computational model 13b. This allows the computational model generation system 100 to inexpensively and appropriately generate a computational model 13b that predicts loosening of the wheel nuts 50.

[0067] The vehicle operation system 110 includes the wheel nut loosening prediction device 10, an operation plan management device 31, and a work plan management device 32 described above. The operation plan management device 31 manages vehicle operation plans. The work plan management device 32 manages maintenance work plans that include retightening of loose wheel nuts 50. When loosening is predicted by the wheel nut loosening prediction device 10, the operation plan management device 31 presents a plan proposal for adding retightening work to the operation plan during free time in the work plan presented by the work plan management device 32. In this way, the vehicle operation system 110 can provide a plan for appropriately performing maintenance to retighten wheel nuts 50, improving convenience for the operation planner.

[0068] The present invention has been described above based on the embodiments. These embodiments are merely examples, and it will be understood by those skilled in the art that various modifications and changes are possible within the scope of the claims of the present invention, and that such modifications and changes also fall within the scope of the claims of the present invention. Therefore, the descriptions and drawings in this specification should be treated as illustrative rather than restrictive. [Explanation of symbols]

[0069] 10 Wheel nut loosening prediction device, 12 Vehicle information acquisition unit, 13 Wheel nut loosening calculation unit, 13b Calculation model, 21 Learning processing unit, 31 Operation plan management device, 32 Work plan management device, 5 Tires, 50 Wheel Nuts, 51 Indicators, 100 computational model generation system, 110 vehicle operation system.

Claims

1. a vehicle information acquisition unit that acquires vehicle information including a mileage of a vehicle and temperatures and air pressures of tires mounted on the vehicle; a wheel nut loosening calculation unit having a calculation model that predicts loosening of wheel nuts of the tire based on input data, the wheel nut loosening calculation unit inputting the vehicle information acquired by the vehicle information acquisition unit into the calculation model to predict loosening of the wheel nuts; A wheel nut loosening prediction device comprising:

2. The wheel nut loosening prediction device described in Claim 1, characterized in that the wheel nut loosening calculation unit has a pre-processing unit that accumulates and consolidates vehicle information acquired by the vehicle information acquisition unit for a certain period of time.

3. 3. The wheel nut loosening prediction device according to claim 1, wherein the input data includes information about the wheel nuts, including thread specifications.

4. The wheel nut loosening prediction device according to any one of claims 1 to 3, wherein the calculation model calculates the probability that the wheel nut is rotating.

5. a vehicle information acquisition step of acquiring vehicle information including a mileage of a vehicle and temperatures and air pressures of tires mounted on the vehicle; a wheel nut looseness calculation step of inputting the vehicle information acquired in the vehicle information acquisition step into a calculation model that predicts loosening of the wheel nuts of the tire based on input data, and predicting loosening of the wheel nuts; A method for predicting wheel nut loosening, comprising:

6. a vehicle information acquisition unit that acquires vehicle information including a mileage of a vehicle and temperatures and air pressures of tires mounted on the vehicle; a wheel nut loosening calculation unit having a calculation model that predicts loosening of wheel nuts of the tire based on input data, the wheel nut loosening calculation unit inputting the vehicle information acquired by the vehicle information acquisition unit into the calculation model to predict loosening of the wheel nuts; a learning processing unit that learns the calculation model by comparing the looseness of the wheel nuts calculated by the wheel nut looseness calculation unit with a change in an indicator that indicates the looseness of the wheel nuts; and A computational model generation system comprising:

7. The wheel nut loosening prediction device according to any one of claims 1 to 4, an operation plan management device that manages an operation plan of the vehicle; a work plan management device that manages a maintenance work plan including retightening the wheel nuts, A vehicle operation system characterized in that, when loosening is predicted by the wheel nut loosening prediction device, the operation plan management device presents a plan proposal to add retightening work to the operation plan during free time in the work plan presented by the work plan management device.

Images