CN116963936A

CN116963936A - Vehicle monitoring method, device, equipment and computer readable storage medium

Info

Publication number: CN116963936A
Application number: CN202180092815.5A
Authority: CN
Inventors: 尹航一; 蒋朋家; 李家鑫
Original assignee: Sichuan Golden Ridge Intelligence Science and Technology Co Ltd
Current assignee: Sichuan Golden Ridge Intelligence Science and Technology Co Ltd
Priority date: 2021-05-20
Filing date: 2021-05-20
Publication date: 2023-10-27
Also published as: WO2022241705A1

Abstract

Embodiments of the present specification provide a vehicle monitoring method, apparatus, device, and computer readable medium. The method comprises the following steps: acquiring operation condition data of a part to be detected of a vehicle, wherein the operation condition data at least comprise a plurality of groups of normal data sets under normal conditions, and each group of normal data sets comprises first operation data and first motion data of the vehicle at a moment corresponding to the first operation data; acquiring at least one group of actual measurement data sets of the part to be detected in actual operation, wherein each group of actual measurement data sets comprises second operation data and second motion data of the vehicle at the moment corresponding to the second operation data; wherein, the first operation data and the second operation data both reflect the operation state information of the part to be detected, and the first movement data and the second movement data both reflect the movement state information of the vehicle; and determining the running state of the part to be detected reflected by each group of measured data sets based on the running condition data and the measured data sets.

Description

Vehicle monitoring method, device, equipment and computer readable storage medium

Technical Field

The present disclosure relates to the field of data monitoring technologies, and in particular, to a vehicle monitoring method, device, apparatus, and computer readable storage medium.

Background

With the development of information technology, vehicles in transportation are increasing. The volume of data generated by vehicles is also increasing, and a large amount of data is mixed together, so that it is more and more difficult to manually monitor the data generated by the vehicles and judge the running information of the vehicles from the data.

It is therefore desirable to provide a vehicle monitoring scheme that enables automatic monitoring of vehicle data.

Disclosure of Invention

One aspect of the present description provides a method of vehicle monitoring, the method comprising: acquiring operation condition data of a part to be detected of a vehicle, wherein the operation condition data at least comprise a plurality of groups of normal data sets under normal conditions, and each group of normal data sets comprises first operation data and first motion data of the vehicle at a moment corresponding to the first operation data; acquiring at least one group of actual measurement data sets of the part to be detected in actual operation, wherein each group of actual measurement data sets comprises second operation data and second motion data of the vehicle at the moment corresponding to the second operation data; wherein, the first operation data and the second operation data both reflect the operation state information of the part to be detected, and the first movement data and the second movement data both reflect the movement state information of the vehicle; and determining the running state of the part to be detected reflected by each group of measured data sets based on the running condition data and the measured data sets.

Another aspect of the present description provides a vehicle monitoring device. The device comprises: the first acquisition module is used for acquiring operation condition data of a part to be detected of the vehicle, wherein the operation condition data at least comprise a plurality of groups of normal data sets under normal conditions, and each group of normal data sets comprises first operation data and first motion data of the vehicle at a moment corresponding to the first operation data; the second acquisition module is used for acquiring at least one group of actual measurement data sets of the part to be detected in actual operation, wherein each group of actual measurement data sets comprises second operation data and second motion data of the vehicle at the moment corresponding to the second operation data; wherein, the first operation data and the second operation data both reflect the operation state information of the part to be detected, and the first movement data and the second movement data both reflect the movement state information of the vehicle; and the state determining module is used for determining the operation state of the part to be detected reflected by each group of the actual measurement data sets based on the operation condition data and the actual measurement data sets.

Another aspect of the present description provides a vehicle monitoring device comprising at least one storage medium for storing computer instructions and at least one processor; the at least one processor is configured to execute the computer instructions to implement a vehicle monitoring method as described in any of the above.

Another aspect of the present disclosure provides a computer-readable storage medium storing computer instructions that, when read by a computer, perform a vehicle monitoring method according to any one of the above aspects.

Possible benefits of embodiments of the present description include, but are not limited to: (1) The working condition of the part to be detected can be rapidly and accurately obtained by comparing the interval between the actual measurement data set and the normal data set of the part to be detected; (2) The running state of the part to be detected is determined by using the data set which is selected by self and meets the actual running condition under various complex working conditions as a training sample and using an intelligent machine learning model obtained by training in a specific model training process, so that the data processing accuracy and the adaptability are high, the monitoring effect of the expected running state information data can be obtained, the data processing efficiency is improved, and the human error is avoided; (3) And the data set in the preset interval is correspondingly screened, so that the interference of external environmental factors is avoided.

Drawings

The present specification will be further elucidated by way of example embodiments, which will be described in detail by means of the accompanying drawings. The embodiments are not limiting, in which like numerals represent like structures, wherein:

FIG. 1 is a schematic illustration of an application scenario of a vehicle monitoring system according to some embodiments of the present disclosure;

FIG. 2 is an exemplary flow chart of a vehicle monitoring method according to some embodiments of the present disclosure;

FIG. 3a is an exemplary graph of vehicle speed versus its corresponding motor current value under normal operating conditions according to some embodiments of the present disclosure;

FIG. 3b is an exemplary plot of actual operating vehicle speed versus its corresponding motor current value, according to some embodiments of the present disclosure;

FIG. 4 is an exemplary flow chart of a method of determining an operational status of a component to be inspected according to some embodiments of the present disclosure;

FIG. 5 is an exemplary flow chart of a method of determining an operational status of a component to be inspected according to further embodiments of the present disclosure;

fig. 6 is a schematic structural view of an exemplary vehicle monitoring device shown in accordance with some embodiments of the present description.

Detailed Description

In order to more clearly illustrate the technical solutions of the embodiments of the present specification, the drawings that are required to be used in the description of the embodiments will be briefly described below. It is apparent that the drawings in the following description are only some examples or embodiments of the present specification, and it is possible for those of ordinary skill in the art to apply the present specification to other similar situations according to the drawings without inventive effort. Unless otherwise apparent from the context of the language or otherwise specified, like reference numerals in the figures refer to like structures or operations.

It should be appreciated that "system," "apparatus," "unit," and/or "module" as used in this specification is a method for distinguishing between different components, elements, parts, portions, or assemblies at different levels. However, if other words can achieve the same purpose, the words can be replaced by other expressions.

As used in this specification and the claims, the terms "a," "an," "the," and/or "the" are not specific to a singular, but may include a plurality, unless the context clearly dictates otherwise. In general, the terms "comprises" and "comprising" merely indicate that the steps and elements are explicitly identified, and they do not constitute an exclusive list, as other steps or elements may be included in a method or apparatus.

A flowchart is used in this specification to describe the operations performed by the system according to embodiments of the present specification. It should be appreciated that the preceding or following operations are not necessarily performed in order precisely. Rather, the steps may be processed in reverse order or simultaneously. Also, other operations may be added to or removed from these processes.

Fig. 1 is a schematic view of an application scenario of a vehicle monitoring system according to some embodiments of the present description.

The scene can be applied to a transportation system and a traffic service system. For example, the scenario may be applied to the monitoring of vehicle data in any area. In some embodiments, the vehicle monitoring system 100 may be applied to data monitoring of intelligent vehicles in scenic spots, factories, ports, schools, and the like.

The vehicle monitoring system 100 may be an online service platform including a server 110, a network 120, a terminal 130, a database 140, and a vehicle 150. The server 110 may contain a processing device 112.

In some embodiments, server 110 may be used to process information and/or data related to monitoring for a vehicle. The server 110 may be a stand-alone server or a group of servers. The server farm may be centralized or distributed (e.g., server 110 may be a distributed system). The server 110 may be regional or remote in some embodiments. For example, server 110 may access information and/or profiles stored in terminal 130, database 140, vehicle 150 via network 120. In some embodiments, server 110 may be directly connected to terminal 130, database 140, vehicle 150 to access information and/or material stored therein. In some embodiments, server 110 may execute on a cloud platform. For example, the cloud platform may include one of a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, or the like, or any combination thereof.

In some embodiments, server 110 may include a processing device 112. The processing device 112 may process data and/or information related to vehicle monitoring to perform one or more of the functions described herein. For example, the processing device 112 may obtain a normal data set and a measured data set. For another example, the processing device 112 may determine the operational status of the component to be inspected based on the normal data set and the measured data set. In some embodiments, the processing device 112 may include one or more sub-processing devices (e.g., a single core processing device or a multi-core processing device). By way of example only, the processing device 112 may include a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), an Application Specific Instruction Processor (ASIP), a Graphics Processor (GPU), a Physical Processor (PPU), a Digital Signal Processor (DSP), a Field Programmable Gate Array (FPGA), an editable logic circuit (PLD), a controller, a microcontroller unit, a Reduced Instruction Set Computer (RISC), a microprocessor, and the like, or any combination thereof.

The network 120 may facilitate the exchange of data and/or information. In some embodiments, one or more components in the vehicle monitoring system 100 (e.g., server 110, terminal 130, database 140, vehicle 150) may send data and/or information to other components over the network 120. In some embodiments, network 120 may be any type of wired or wireless network. For example, the network 120 may include a cable network, a wired network, a fiber optic network, a telecommunications network, an internal network, the Internet, a Local Area Network (LAN), a Wide Area Network (WAN), a Wireless Local Area Network (WLAN), a Metropolitan Area Network (MAN), a Public Switched Telephone Network (PSTN), a Bluetooth network, a ZigBee network, a Near Field Communication (NFC) network, and the like, or any combination thereof. In some embodiments, network 120 may include one or more network access points. For example, network 120 may include wired or wireless network access points, such as base station and/or Internet switching points 120-1, 120-2, …, through which one or more components of system 100 may connect to network 120 to exchange data and/or information.

The terminal 130 may be used to input and/or obtain data and/or information. In some embodiments, the terminal 130 may include a smart phone 130-1, a tablet 130-2, a laptop 130-3, and the like. In some embodiments, terminal 130 may comprise a mobile terminal device or the like. For example, the mobile device may include a smart home device, a wearable device, a smart mobile device, a virtual reality device, an augmented reality device, and the like, or any combination of the above examples. In some embodiments, the smart home devices may include smart lighting devices, control devices for smart appliances, smart monitoring devices, smart televisions, smart cameras, interphones, and the like, or any combination of the above examples. In some embodiments, the wearable device may include a wristband, footwear, glasses, helmet, watch, clothing, backpack, smart accessory, or the like, or any combination of the above examples. In some embodiments, the smart mobile device may include a mobile handset, a personal digital assistant, a gaming device, a navigation device, a POS, a laptop, a desktop, or the like, or any combination of the above examples.

In some embodiments, the user may obtain the operating state of the vehicle through the terminal 130. In some embodiments, the user may obtain the normal data set and the measured data set of the vehicle through the terminal 130.

Database 140 may store materials and/or instructions. In some embodiments, database 140 may store material obtained from terminal 130. In some embodiments, database 140 may store information and/or instructions for execution or use by server 110 to perform the exemplary methods described in this disclosure. In some embodiments, database 140 may store normal data sets, measured data sets, machine learning models, and the like. In some embodiments, database 140 may include mass storage, removable storage, volatile read-write memory (e.g., random access memory, RAM), read-only memory (ROM), and the like, or any combination thereof. In some embodiments, database 140 may be implemented on a cloud platform. For example, the cloud platform may include a private cloud, a public cloud, a hybrid cloud, a community cloud, a decentralized cloud, an internal cloud, and the like, or any combination thereof.

The vehicle 150 may include various types of vehicles, such as a bicycle, electric vehicle, motorcycle, automobile, truck, van, etc. In some embodiments, the vehicle 150 may send the acquired data to one or more devices in the vehicle monitoring system 100. For example, the vehicle 150 may send the acquired data to the server 110 via the network 120 for subsequent steps. In some embodiments, the vehicle 150 may communicate with one or more devices in the vehicle monitoring system 100. For example, vehicle 150 may communicate with terminal 130 over network 120. As another example, the vehicle 150 may communicate directly with the terminal 130. In some embodiments, the data of the vehicle 150 may be stored in the database 140.

In some embodiments, database 140 may be connected to network 120 to communicate with one or more components of system 100 (e.g., server 110, terminal 130, vehicle 150, etc.). One or more components of system 100 may access materials or instructions stored in database 140 via network 120. For example, the server 110 may extract the normal data set, the measured data set, the machine learning model, etc. from the database 140 and perform the corresponding processing. In some embodiments, database 140 may be directly connected to or in communication with one or more components in system 100 (e.g., server 110, terminal 130, vehicle 150). In some embodiments, database 140 may be part of server 110.

FIG. 2 is an exemplary flow chart of a method of vehicle monitoring according to some embodiments of the present description.

As shown in fig. 2, the process 200 may be performed by a processing device (e.g., server 110), a vehicle monitoring system (e.g., system 100), or a vehicle monitoring apparatus (e.g., apparatus 600). It comprises the following steps:

step 210, operation condition data of a part to be detected of the vehicle is obtained, the operation condition data at least comprises a plurality of groups of normal data sets under normal conditions, and each group of normal data sets comprises first operation data and first motion data of the vehicle at a moment corresponding to the first operation data.

The component to be detected is a component to be detected in the vehicle. In some embodiments, the component to be detected may include, but is not limited to, a motor, an engine, a transmission, an electronically controlled power steering system, an automatic air conditioning system, an automatic transmission electronic control system, and the like.

Operating condition data refers to data generated by a vehicle during one or more (at least two) operating conditions. For example, the operating conditions of the vehicle include, but are not limited to, normal conditions, abnormal conditions, aging conditions, conditions to be serviced, etc. In some embodiments, the operating condition data may include several sets of normal data sets for normal conditions. In some embodiments, the operating condition data may include at least one of the following in addition to several sets of normal data sets under normal conditions: an abnormal data set under an abnormal working condition, a plurality of groups of ageing data sets under ageing working conditions and a plurality of groups of data sets to be maintained under the working conditions to be maintained.

The normal data set is a data set generated under normal working conditions of the vehicle, and for example, the normal data set may include an odometer value, a battery compartment temperature, a battery compartment humidity, a battery capacity, a sensor operation condition and the like of the vehicle under a normal state. For another example, the normal data set may also include a set of data such as a speed, a voltage value, a tension value, a position, an acceleration, etc. of the vehicle at a certain time or for a certain period of time.

A set of normal data includes a first operational data, and a first movement data of the vehicle at a time corresponding to the first operational data. In some embodiments, the first operating data may be one or more current values of the motor under normal operating conditions, and the first motion data may be one or more speeds of the vehicle at a time corresponding to the one or more current values. In some embodiments, the first operating data may be one or more power values of the motor under normal operating conditions, and the first motion data may be one or more accelerations of the vehicle at times corresponding to the one or more power values of the motor. In some embodiments, the first operating data may be one or more power values of the engine under normal operating conditions, and the first movement data may be one or more amounts of exhaust of the vehicle at a time corresponding to the one or more power values of the vehicle. For example, when the vehicle runs to 10 minutes under the normal working condition, the first operation data is a motor current value 50A, and the corresponding first movement data (speed) of the vehicle is 60km/h. For another example, when the vehicle is driven to 30 minutes under the normal working condition, the first operation data is that the motor power value is 10kw, and the corresponding first movement data (speed) of the vehicle is 110km/h.

In some embodiments, the vehicle may be driven under normal conditions to obtain multiple sets of normal data sets. The plurality of sets of normal data may include a plurality of sets of first operational data and a plurality of sets of first movement data during travel of the vehicle.

A data set is a collection of data that a vehicle generates while running. The vehicle may be any type of vehicle, and may include, for example, a mini-vehicle, a medium-sized vehicle, and a large-sized vehicle. As another example, the vehicle may include a car, truck, coach, trailer, incomplete vehicle, motorcycle, or the like.

In some embodiments, the data set may include system resource data, hardware state data, hardware data, software module operational data. In some embodiments, the data set may include lower computer sensor data, lower computer system resource data, lower computer sensor status data, upper computer sensor status data, upper computer system resource data, upper computer business software operation data, upper computer business software resource occupancy data.

In some embodiments, the data sets may be collected in the form of publications and subscriptions to topics. For example, only the corresponding data needs are issued during the acquisition, so that only the required data is acquired.

In some embodiments, the data set may include, but is not limited to, current values, voltage values, mileage, acceleration, tension, position, inertia, gasoline level, light detection, and ranging, etc., corresponding to the time of vehicle operation.

In some embodiments, the data set of the vehicle may be detected by a sensor or a measurement unit of the vehicle. In some embodiments, the data set may be used to include cloud storage presentation analysis, human-machine interaction, software business, remote problem location, remote debugging, big data analysis.

The manner in which the data set is acquired may be in any feasible manner. In some embodiments, the data set may be obtained by reading stored data, invoking an associated interface, or otherwise. For example, through network transmission or direct uploading. For another example, the vehicle may upload the data set over a network and the processing device may then acquire. In some embodiments, the acquired data set may be stored in database 140.

The operation data are data of the part to be detected of the vehicle in a driving state. The operational data may include current value, voltage value, power of the motor. The operating data may also include engine output power, output energy, torque, etc. The first operation data, the second operation data, the third operation data, the fourth operation data and the fifth operation data are the operation data in different states.

The motion data is data in a vehicle motion state. For example, the motion data may include speed, acceleration, displacement, etc. of the vehicle as it moves. The first motion data, the second motion data, the third motion data, the fourth motion data and the fifth motion data are data of the motion data in different states.

Step 220, obtaining at least one group of actual measurement data sets of the part to be detected in actual operation, wherein each group of actual measurement data sets comprises second operation data and second motion data of the vehicle at the moment corresponding to the second operation data; the first operation data and the second operation data reflect the operation state information of the part to be detected, and the first movement data and the second movement data reflect the movement state information of the vehicle.

The actual measurement data set is the data set obtained by measuring the part to be detected in actual operation. The actual measurement data set corresponds to the normal data set and represents the actual running condition of the part to be detected of the vehicle.

The set of measured data includes a second operational data and a second movement data of the vehicle at a time corresponding to the second operational data. For example, when the vehicle is running to 20 minutes in actual operation, the second operation data is the motor current value 50A, and the corresponding second movement data (speed) of the vehicle at this time is 50km/h. In some embodiments, the vehicle will have multiple sets of measured data sets available during actual operation. The plurality of sets of measured data may include a plurality of sets of second operational data and a plurality of sets of second motion data during travel of the vehicle.

In some embodiments, the type of motion data and operational data may be determined based on the type of component to be detected. For example, the component to be detected is a motor, and it may be determined that the type of the operation data is a motor current value or voltage value, etc., and the motion data is a car speed or acceleration, etc. For another example, the component to be detected is an engine, and it may be determined that the type of the operation data is the power of the engine and the motion data is the acceleration of the automobile. In some embodiments, the second operational data of the measured data set is the same as the first operational data of the normal data set, and the second motion data of the measured data set is the same as the second operational data of the normal data set. For example, if the first operation data of the normal data set is a current value of the motor, the second operation data of the measured data set is also a current value of the motor. The first motion data of the normal data set is the speed of the vehicle and the second motion data of the measured data set is the speed of the vehicle. For another example, the first operating data of the normal data set is a power value of the engine, and the second operating data of the measured data set is also a power value of the engine. The first motion data of the normal data set is the acceleration of the vehicle, and the second motion data of the measured data set is the acceleration of the vehicle.

In some embodiments, the acquisition interval duration of the measured data set may be determined according to the type of component to be detected. The acquisition interval duration is the time length of the interval for acquiring the actual measurement data set. For example, the acquisition interval period may be shortened for a high-importance part to be detected, and the acquisition interval period may be increased for a low-importance part to be detected. For example, the component to be detected is an engine, and the duration of the acquisition interval of the measured data set may be set to be 30 seconds, which means that the measured data set is acquired once at intervals of 30 seconds. For another example, the component to be detected is a motor, and the acquisition interval duration of the actual measurement data set may be set to be 40 seconds, which means that the actual measurement data set is acquired once at intervals of 40 seconds. According to the characteristics of the components to be detected of different types, the corresponding setting of the acquisition interval time length of the actual measurement data set is carried out, so that the data sets meeting different expected demands can be acquired more pertinently, and the acquisition efficiency of the actual measurement data set is improved.

Step 230, determining the operation state of the component to be detected reflected by each set of measured data sets based on the operation condition data and the measured data sets.

In some embodiments, the operational state of the component to be inspected reflected by each set of measured data sets may be determined based on several sets of normal data sets. The plurality of sets of normal data includes a plurality of sets of first operational data and first motion data.

In some embodiments, a maximum value and a minimum value of a plurality of first motion data corresponding to each first operation data of the plurality of normal data sets may be analyzed, and when the second operation data is the same as the first operation data, the maximum value and the minimum value of the first motion data are compared with the second motion data corresponding to the one set of measured data sets. The operation state of the part to be detected can be obtained after comparison. For example, taking a motor as an example, comparing a current value at a certain speed of a set of measured data sets with a maximum or minimum current value at the speed of a normal data set, if the current values of the two differ by more than a threshold value, the motor state may be considered abnormal, and if the current values of the two differ by not more than a threshold value, the motor state may be considered normal. Specifically, the current values corresponding to 50km/h under the normal data set include 10A, 12A and 14A. The threshold was set at 0.5A and the maximum current value for the normal data set was 14A at 50 km/h. The current value corresponding to 50km/h under the actual measurement data set is 14.2A, and the current value does not exceed the threshold value of 0.5A compared with 14A, so that the motor state can be considered to be normal.

In some embodiments, the average value of the plurality of first motion data may be obtained by processing the plurality of first motion data corresponding to each first operation data in the normal data set, and the operation state of the component to be detected may be obtained by comparing the second motion data in the measured data set with the average value. Taking the engine as an example, several sets of power values at a certain speed of the normal data set may be processed to obtain an average power value at that speed. The average power value is compared with the power value of the speed under the measured data set, if the power value of the average power value and the power value of the speed under the measured data set differ by more than a threshold value, the engine state can be considered to be abnormal, and if the power value of the average power value and the power value of the speed under the measured data set differ by not more than the threshold value, the engine state can be considered to be normal. Specifically, the power value corresponding to 50km/h under the normal data set includes 500kw, 600kw and 700kw, and the average power value of 50km/h of the normal data set is 600kw. The threshold was set at 150kw. The power value corresponding to 50km/h under the actual measurement data set is 440kw, the difference between 440kw and 600kw is 160kw, and when the threshold value is exceeded, the engine state is considered to be abnormal.

In some embodiments, the normal data interval of the first operation data corresponding to each first motion data may be determined based on several sets of normal data sets. And when the first motion data is the same as the second motion data, comparing the second motion data corresponding to the second motion data with the normal data interval corresponding to the first motion data, and obtaining a comparison result. Based on the comparison result, the operating state of the component to be detected is determined. As shown in fig. 3a and 3b, the motor is taken as operation data and the vehicle speed is taken as motion data as an example. The running state of the part to be detected can be obtained rapidly and accurately by matching and comparing the interval of the actual measurement data set and the normal data set of the part to be detected, and the method is particularly suitable for the working condition with less complex monitoring condition.

FIG. 3a is an exemplary graph of vehicle speed versus its corresponding motor current value under normal operating conditions according to some embodiments of the present disclosure. Fig. 3b is an exemplary graph of actual operating vehicle speed versus its corresponding motor current value, according to some embodiments of the present disclosure.

Under actual running, the value of the second running data corresponding to the automobile speed of 10km/h is 8A, and under normal working conditions, the interval of the values of the first running data corresponding to the automobile speed of 10km/h is 2A-11A. When the speed is 10km/h, the value of the second operation data is in the normal interval of the first operation data, so the actual measurement data set reflects the normal of the part to be detected.

Under actual running, the value of the second running data corresponding to the automobile speed of 30km/h is 20A, and under normal working condition, the interval of the values of the first running data corresponding to the automobile speed of 30km/h is 4A-18A. When the speed is 30km/h, the value of the second operation data is not in the normal interval of the first operation data, so the actual measurement data set reflects that the part to be detected is abnormal.

Under actual running, the value of the second running data corresponding to the automobile speed at 50km/h is 20A, and under normal working conditions, the interval of the values of the first running data corresponding to the automobile speed at 50km/h is 10A-25A. When the speed is 50km/h, the value of the second operation data is in the normal interval of the first operation data, so the actual measurement data set reflects the normal of the part to be detected.

In some embodiments, when the measured data set reflects that the number of abnormal parts to be detected is greater than a threshold, a corresponding overhaul program is started to overhaul the parts to be detected. For example, when the actually measured data set in the motor reflects that the number of abnormal parts to be detected is greater than 10, a corresponding overhaul program is started to overhaul the motor.

FIG. 4 is an exemplary flow chart of a method of determining an operational status of a component to be inspected according to some embodiments of the present disclosure.

In some embodiments, the operating condition data includes an abnormal data set during an abnormal condition in addition to the sets of normal data sets during normal conditions.

As shown in fig. 4, the process 400 may be performed by a processing device (e.g., server 110), a vehicle monitoring system (e.g., system 100), or a vehicle monitoring apparatus (e.g., apparatus 600). It comprises the following steps:

step 410, acquiring a plurality of sets of normal data sets of a part to be detected of the vehicle under normal working conditions.

The details of step 410 are the same as those of step 210, see step 210, and are not repeated here.

Step 420, obtaining abnormal data sets of the to-be-detected part of the vehicle under abnormal working conditions, wherein each abnormal data set comprises third operation data, and the third operation data corresponds to third motion data of the vehicle at the moment.

In some embodiments, the abnormal data set is a data set generated by a component of the vehicle to be detected under abnormal conditions. Such as a data set generated by the component to be tested in the event of a fault. In some embodiments, the data sets include normal data sets and abnormal data sets, and the abnormal data sets may be obtained by filtering the normal data sets by the data sets.

In some embodiments, the abnormal data set includes third operational data and third motion data of the vehicle at a time corresponding to the third operational data. Wherein the third operation data reflects the operation state information of the part to be monitored of the vehicle, and the third movement data reflects the movement state information of the vehicle. For an explanation of the operational data and the movement data, reference may be made to the relevant description of fig. 2.

The component to be detected may be any feasible component in the vehicle, the first external data and the second external data may be any feasible data types capable of reflecting the running environment information of the vehicle, and the first running data, the second running data and the third running data may be any feasible data types capable of reflecting the running state information of the component to be monitored of the vehicle. The first, second, and third motion data may be any feasible data type capable of reflecting motion state information of the vehicle.

In some embodiments, the component to be detected may comprise a motor; the first external data may include at least a road gradient value and/or a vehicle load, for example, the first external data may be a road gradient value and a vehicle load, and the second external data may include at least a road gradient value and/or a vehicle load, for example, the second external data may be only a road gradient value or a vehicle load; the first operation data may include at least a current value of the motor, the second operation data may include at least a current value of the motor, and the third operation data may include at least a current value of the motor; the first motion data may include at least a travel speed of the vehicle, the second motion data may include at least a travel speed of the vehicle, and the third motion data may include at least a travel speed of the vehicle. The selected road gradient value, the vehicle load, the current value of the motor and the running speed of the vehicle can reflect the running state of the part to be detected of the vehicle, and the representative road gradient value, the vehicle load, the current value of the motor and the running speed of the vehicle are good, so that the running state of the part to be detected can be calculated and monitored more accurately and efficiently.

Step 430, training the initial first machine learning model with the normal data set as positive samples and the abnormal data set as negative samples to obtain a trained first machine learning model.

In some embodiments, the initial first machine learning model may be a classifier. In some embodiments, a logistic regression model, support vector machine, random forest or other classification model, etc. may be used as the classifier.

The initial first machine learning model training samples are a normal data set and an abnormal data set. Positive samples are normal data sets and labels are normal. The negative samples are abnormal data sets and the labels are abnormal.

In some embodiments, the data set may also include external data. The external data may include first external data and second external data. Both the first external data and the second external data may reflect vehicle operating environment information, and the external data may interfere with the determination of the last to-be-detected component state to some extent. It will be appreciated that when the external data is different, the data results of the normal data set and the measured data set will also have corresponding errors.

In some embodiments, the external data may include road grade values and/or vehicle load. The gradient of a road indicates the angle of the traveling road to the level ground. For example, the gradient of the road may be 3 degrees, 5 degrees, etc. The vehicle load represents the weight of the load-bearing object on the vehicle, and for example, the vehicle load may be 1 ton, 3 tons, or the like.

In some embodiments, the data set may also include external data of the vehicle at the time the operational data corresponds. For example, when the current value of the motor is 10A, the gradient of the road is 5 degrees at the corresponding moment.

In some embodiments, the normal data set includes first external data of the vehicle at a time corresponding to the first operational data. The normal data set corresponding to the first external data located within the first preset interval may be taken as a positive sample. For example, the first external data is a road gradient value, the first preset interval is 0 to 5 degrees, and a normal data set located at 0 to 5 degrees is taken as a positive sample.

In some embodiments, the abnormal data set includes second external data of the vehicle at a time corresponding to the second operational data. The normal data set corresponding to the second external data located within the second preset interval may be taken as a positive sample. For example, the second external data is a road gradient value, the second preset interval is 0 to 5 degrees, and an abnormal data set located at 0 to 5 degrees is taken as a negative sample.

In some embodiments, the first preset interval may be the same as or different from the second preset interval, and it may be understood that screening the data sets in the preset interval may effectively compare the interference of the external environment to the data sets.

In some embodiments, training the initial first machine learning model may be performed using conventional methods, such as gradient descent methods. In some embodiments, the initial machine learning model may also be trained using the Levenberg-Marquardt algorithm (LM algorithm, also known as the attenuated least squares method) to obtain a trained first machine learning model. The LM algorithm is relatively suitable for medium-small networks for screening vehicle fault points, such as BP neural network models and the like.

Step 440, determining, based on the actual measurement data sets, whether the operation state of the component to be detected reflected by each set of actual measurement data sets is normal or abnormal, using the trained first machine learning model.

In some embodiments, a set of measured data sets is input into a trained first machine learning model, and the operating state of the component to be detected reflected by the measured data sets can be obtained. For example, the component to be detected in the measured data set may be a motor, and the operation data may be a current value of the motor. The movement data may be a speed at which the vehicle is traveling. The current value 10A of the motor and the running speed of the vehicle of 30km/h can be input into the trained first machine school model to obtain a final output result which is normal, and the running state of the part to be detected is normal. For another example, the current value 20A of the motor may be input to the trained first machine school model at a running speed of 40km/h to obtain a final output result that is abnormal, which indicates that the running state of the component to be detected is abnormal.

FIG. 5 is an exemplary flow chart of a method of determining an operational status of a component to be inspected according to further embodiments of the present disclosure.

In some embodiments, the operating condition data may also include sets of aging data sets for aging conditions, sets of data sets to be maintained for maintenance conditions.

As shown in fig. 5, the process 500 may be performed by a processing device (e.g., server 110), a vehicle monitoring system (e.g., system 100), or a vehicle monitoring apparatus (e.g., apparatus 600). It comprises the following steps:

step 510, acquiring a plurality of groups of aging data sets of the part to be detected under an aging working condition, wherein each group of aging data sets comprises fourth operation data and fourth motion data of the vehicle at a moment corresponding to the fourth operation data; acquiring a plurality of groups of to-be-maintained data sets of the to-be-detected component under the to-be-maintained working condition, wherein each group of to-be-maintained data sets comprises fifth operation data and fifth motion data of the vehicle at the moment corresponding to the fifth operation data; the fourth running data and the fifth running data reflect running state information of the part to be detected, and the fourth running data and the fifth running data reflect running state information of the vehicle.

In some embodiments, several sets of aging data sets of the component to be detected of the vehicle under the aging condition are acquired, and each set of aging data sets includes fourth operation data, and fourth motion data of the vehicle at a time corresponding to the fourth operation data.

And acquiring a plurality of groups of to-be-maintained data sets of the to-be-detected part of the vehicle under the to-be-maintained working condition, wherein each group of to-be-maintained data sets comprises fifth operation data, and the fifth operation data corresponds to fifth motion data of the vehicle at the moment.

In some embodiments, the fourth operational data and the fifth operational data correspond to the first operational data of the normal data set, respectively, and the fourth motion data and the fifth motion data correspond to the first motion data of the normal data set, respectively. Which represents data under different operating conditions.

In some embodiments, the operation condition data and/or the collection of the measured data set may be performed by at least one or a combination of a visual sensor, a motor hall sensor, an inertial sensor, and a GPS positioning device. Specifically, the vision sensor may be used to acquire imaging noise detection data so as to judge the operation state of the vehicle glass member in front of the vision sensor, such as the aging condition of the vehicle glass, etc., by the imaging noise detection data; the motor hall sensor and the GPS positioning device are combined, so that the motor hall sensor can be used for acquiring speed data, pulse abnormal data, noise data and/or frequency data, and judging the running state of the motor hall sensor through the speed data, the pulse abnormal data, the noise data and/or the frequency data, for example, judging whether the pulse is abnormal or not according to whether the speed output by the motor hall sensor is matched with the real speed or not, for example, judging the health state of the motor hall sensor according to the noise data and the frequency data; the inertial sensors may be used to obtain positioning data, speed and/or acceleration data of the vehicle to provide a data basis for further analysis to determine the operational status of the vehicle or some component of the vehicle to be detected.

By adopting the data acquisition device or the combination of the data acquisition devices, expected specific operation condition data and/or actual measurement data sets can be acquired more efficiently, and a favorable data basis is provided for subsequent data analysis and calculation.

And step 520, training the initial second machine learning model by taking the normal data set, the aging data set and the data set to be maintained as training samples to obtain a trained second machine learning model.

The initial second machine learning model training samples are a normal data set, an aging data set and a data set to be maintained, the labels are normal, aging and the data set to be maintained respectively, the normal data set, the aging data set and the data set to be maintained are used as training samples, and a preset algorithm is used for training the initial machine learning model. The model introduction, training method, specific algorithm, etc. are similar to those of fig. 4, and detailed description thereof with reference to fig. 4 is omitted here.

In some embodiments, the loss function is optimized by adjusting parameters (e.g., parameters such as learning rate, iteration number, batch size, etc.) of the initial second machine learning model, and when the loss function meets the preset condition, training is ended, resulting in a trained second machine learning model.

In some embodiments, the training sample is used for collecting a normal data set, an aging data set and a maintenance data set in the whole life cycle of the part to be detected, and the data in the whole life cycle can comprehensively reflect the running state of the part to be detected, so that the data richness and the representativeness of the training sample are higher.

In some embodiments, the LM algorithm may also be used to train the initial machine learning model, obtaining a trained second machine learning model. In some embodiments, the BP neural network model is trained using labeled training sample data for the full life cycle of multiple motors until it converges steadily (recognition rate is no longer increasing) and is substantially expected (possibly with some access to the original label, but possibly more reasonable).

In some embodiments, the process of training the BP neural network model using the LM algorithm may be performed as the following steps:

step 1, providing a training error allowable value e, coefficients a and b, and an initialization weight and a threshold vector x (0), wherein k=0 and a=a0;

Step 2, calculating network output and an error index function E (x (k));

step 3, calculating a Jacobian matrix J (x);

step 4, respectively calculating delta_x and E (x (k));

step 5, if E (x (k)) < E, go to step 7; otherwise, calculating x (k+1) and calculating an error index function E (x (k+1)) by taking the x (k+1) as a weight and a threshold;

step 6, if E (x (k+1)) < E (x (k)), let k=k+1, a=a/b, return to step 2; otherwise, the weight and the threshold are updated this time, let x (k+1) =x (k), a=ab, and return to step 4.

And 7, finishing training.

The values of all training parameters such as the training error allowable value e, the coefficients a and b, the initialization weight and the threshold vector x may be set according to the specific training process, and are not particularly limited herein.

In some embodiments, the training process of the LM algorithm on the BP neural network model may be performed using gradient vectors and jacobian matrices.

By utilizing the LM algorithm to specifically train the BP neural network model, a trained machine learning model with expected convergence and high recognition rate can be obtained, and the model is particularly suitable for application scenes of vehicle complex fault point screening.

Step 530, based on the measured data sets, using the trained second machine learning model, determining whether the operating state of the component to be detected reflected by each set of measured data sets is normal, aged or to be repaired.

In some embodiments, a trained second machine learning model may be used to determine the operational status of the component to be inspected for which each set of measured data is reactive. For example, a set of measured data sets is input into a trained second machine learning model, and the operating state of the component to be detected reflected by the measured data sets can be obtained. In some embodiments, the component to be detected may be a motor and the operational data may be a current value of the motor. The movement data may be a speed at which the vehicle is traveling. For example, the current value 10A of the motor may be input to the trained first machine school model at a running speed of 10km/h to obtain a final output result as aging, which indicates that the running state of the component to be detected is aging. For another example, the current value 30A of the motor may be input to the trained first machine school model at a running speed of 10km/h to obtain a final output result as to-be-maintained, which indicates that the running state of the component to be detected is to-be-maintained.

In some embodiments, current, acceleration, speed, gradient value, vehicle body bearing information and the like of a vehicle in a real-time operation scene are recorded and uploaded to a cloud end, a date of the vehicle put into operation is taken as a starting point, time is recorded, an actual measurement data set is generated in a unit of day and is input into a machine learning model after training, neural network output of the same day is recorded, and finally guiding advice of vehicle maintenance is provided for an operator according to a multi-day output result of the neural network. Illustratively, the aging condition of the glass in front of the vision sensor can be judged according to the imaging noise detection information data of the vision sensor; the health state of the Hall sensor can be finally judged by combining navigation positioning data (judging whether the speed output by the Hall sensor is matched with the real speed) and pulses (judging pulse abnormality through noise, frequency and the like) of the Hall sensor with high precision.

Fig. 6 is a schematic structural view of a vehicle monitoring device according to some embodiments of the present description.

In some embodiments, the vehicle monitoring device 600 may include a first acquisition module 610, a second acquisition module 620, and a state determination module 630. These modules may also be implemented as an application program or as a set of instructions for execution by a processing engine. Furthermore, a module may be any combination of hardware circuitry and applications/instructions. For example, a module may be part of a processor when the processing engine or processor executes an application/set of instructions.

The first obtaining module 610 is configured to obtain operation condition data of a component to be detected of the vehicle, where the operation condition data includes at least several sets of normal data sets under normal conditions, and each set of normal data sets includes first operation data and first motion data of the vehicle at a time corresponding to the first operation data; a second obtaining module 620, configured to obtain at least one set of actual measurement data sets of the component to be detected in actual operation, where each set of actual measurement data sets includes second operation data, and second motion data of the vehicle at a time corresponding to the second operation data; the first running data and the second running data reflect running state information of the part to be detected, and the first running data and the second running data reflect running state information of the vehicle; the state determining module 630 is configured to determine, based on the operating condition data and the actual measurement data sets, an operating state of the component to be detected reflected by each set of actual measurement data sets.

In some embodiments, the second acquisition module 620 is to: determining the acquisition interval duration of the actual measurement data set according to the type of the part to be detected; the interval acquiring interval duration acquires each group of measured data sets.

In some embodiments, the state determination module 630 is to: based on a plurality of groups of normal data sets, determining a normal data interval of first operation data corresponding to each first motion data; based on the actual measurement data set and the normal data interval, when the first motion data is determined to be the same as the second motion data, comparing the second operation data corresponding to the second motion data with the normal data interval corresponding to the first motion data, and obtaining a comparison result; based on the comparison result, the operating state of the component to be detected is determined.

In some embodiments, the operating condition data further includes an abnormal data set during an abnormal condition, and the state determination module 630 is configured to: acquiring abnormal data sets of the part to be detected under abnormal working conditions, wherein each abnormal data set comprises third operation data and third motion data of the vehicle at a moment corresponding to the third operation data; wherein the third operation data reflects the operation state information of the part to be detected, and the third movement data reflects the movement state information of the vehicle; taking the normal data set as a positive sample, taking the abnormal data set as a negative sample, and training the initial first machine learning model by using the positive sample and the negative sample to obtain a trained first machine learning model; based on the actual measurement data sets, a first machine learning model after training is used for determining whether the running state of the part to be detected reflected by each group of actual measurement data sets is normal or abnormal.

In some embodiments, each set of normal data further includes first external data of the vehicle at a time corresponding to the first operational data, each set of abnormal data further includes second external data of the vehicle at a time corresponding to the third operational data, each of the first external data and the second external data reflecting operational environmental information of the vehicle; taking the normal data set as a positive sample and the abnormal data set as a negative sample, comprising: taking a normal data set corresponding to the first external data in the first preset interval as a positive sample; and taking the abnormal data set corresponding to the second external data in the second preset interval as a negative sample.

In some embodiments, the component to be detected includes a motor, each of the first external data and the second external data includes at least a road gradient value and/or a vehicle load, each of the first operation data, the second operation data, and the third operation data includes at least a current value of the motor, and each of the first movement data, the second movement data, and the third movement data includes at least a travel speed of the vehicle.

In some embodiments, the operating condition data further includes several sets of aging data sets for aging conditions, several sets of data sets to be maintained for to-be-maintained conditions, and the state determination module 630 is configured to: acquiring a plurality of groups of aging data sets of a part to be detected under an aging working condition, wherein each group of aging data sets comprises fourth operation data and fourth motion data of a vehicle at a moment corresponding to the fourth operation data; acquiring a plurality of groups of to-be-maintained data sets of the to-be-detected component under the to-be-maintained working condition, wherein each group of to-be-maintained data sets comprises fifth operation data and fifth motion data of the vehicle at the moment corresponding to the fifth operation data; the fourth running data and the fifth running data reflect running state information of the part to be detected, and the fourth running data and the fifth running data reflect running state information of the vehicle; taking the normal data set, the aging data set and the data set to be maintained as training samples, and training an initial second machine learning model to obtain a trained second machine learning model; based on the measured data sets, a second machine learning model after training is used to determine whether the operating state of the component to be detected reflected by each set of measured data sets is normal, aged or to be maintained.

In some embodiments, the collection of the operating condition data and/or the measured data set may be performed using at least one or a combination of a visual sensor, a motor hall sensor, an inertial sensor, and a GPS positioning device. Specifically, the vision sensor may be used to acquire imaging noise detection data so as to judge the operation state of the vehicle glass member in front of the vision sensor, such as the aging condition of the vehicle glass, etc., by the imaging noise detection data; the motor hall sensor and the GPS positioning device are combined, so that the motor hall sensor can be used for acquiring speed data, pulse abnormal data, noise data and/or frequency data, and judging the running state of the motor hall sensor through the speed data, the pulse abnormal data, the noise data and/or the frequency data, for example, judging whether the pulse is abnormal or not according to whether the speed output by the motor hall sensor is matched with the real speed or not, for example, judging the health state of the motor hall sensor according to the noise data and the frequency data; the inertial sensors may be used to obtain positioning data, speed and/or acceleration data of the vehicle to provide a data basis for further analysis to determine the operational status of the vehicle or some component of the vehicle to be detected.

In some embodiments, training the initial machine learning model includes, using the normal data set, the aged data set, and the data set to be repaired as training samples: and training the initial machine learning model by using a preset algorithm by taking the normal data set, the ageing data set and the data set to be maintained as training samples.

step 2, calculating network output and an error index function E (x (k));

step 3, calculating a Jacobian matrix J (x);

step 4, respectively calculating delta_x and E (x (k));

And 7, finishing training.

Some embodiments of the present description also provide a vehicle monitoring device comprising at least one storage medium for storing computer instructions and at least one processor; at least one processor is configured to execute computer instructions to implement the method as in any of the embodiments described above.

Some embodiments of the present description also provide a computer-readable storage medium storing computer instructions that, when read by a computer, perform a method as in any of the embodiments described above.

It should be appreciated that the illustrated system and its modules may be implemented in a variety of ways. For example, in some embodiments, the system and its modules may be implemented in hardware, software, or a combination of software and hardware. Wherein the hardware portion may be implemented using dedicated logic; the software portions may then be stored in a memory and executed by a suitable instruction execution system, such as a microprocessor or special purpose design hardware. Those skilled in the art will appreciate that the methods and systems described above may be implemented using computer executable instructions and/or embodied in processor control code, such as provided on a carrier medium such as a magnetic disk, CD or DVD-ROM, a programmable memory such as read only memory (firmware), or a data carrier such as an optical or electronic signal carrier. The system of the present application and its modules may be implemented not only with hardware circuitry such as very large scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., but also with software executed by various types of processors, for example, and with a combination of the above hardware circuitry and software (e.g., firmware).

It should be noted that the above description of the vehicle monitoring device 600 and its modules is for convenience of description only and is not intended to limit the present disclosure to the scope of the illustrated embodiments. It will be appreciated by those skilled in the art that, given the principles of the system, various modules may be combined arbitrarily or a subsystem may be constructed in connection with other modules without departing from such principles. For example, the first acquiring module 610, the second acquiring module 620, and the state determining module 630 may share one storage module, and each module may have a respective storage module. Such variations are within the scope of the application.

In addition, it should be noted that, the vehicle monitoring device, the computer readable storage medium and the vehicle monitoring method provided in the embodiments of the present disclosure belong to the same inventive concept, and the specific embodiment process may be detailed in the method embodiment, which is not repeated herein.

Possible benefits of embodiments of the present description include, but are not limited to: (1) The working condition of the part to be detected can be rapidly and accurately obtained by comparing the interval between the actual measurement data set and the normal data set of the part to be detected; (2) The running state of the part to be detected is determined by the intelligent machine learning model obtained through training through the specific model training process by taking the data set which is selected by self and meets the actual running condition under various complex working conditions as a training sample, the data processing accuracy and the adaptability are both high, the monitoring effect of the expected running state information data can be obtained, the data processing efficiency is improved, and the human error is avoided. (3) And the data set in the preset interval is correspondingly screened, so that the interference of external environmental factors is avoided. It should be noted that, the advantages that may be generated by different embodiments may be different, and in different embodiments, the advantages that may be generated may be any one or a combination of several of the above, or any other possible advantages that may be obtained.

While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations to the present disclosure may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this specification, and therefore, such modifications, improvements, and modifications are intended to be included within the spirit and scope of the exemplary embodiments of the present invention.

Meanwhile, the specification uses specific words to describe the embodiments of the specification. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present description. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various positions in this specification are not necessarily referring to the same embodiment. Furthermore, certain features, structures, or characteristics of one or more embodiments of the present description may be combined as suitable.

Furthermore, those skilled in the art will appreciate that the various aspects of the specification can be illustrated and described in terms of several patentable categories or circumstances, including any novel and useful procedures, machines, products, or materials, or any novel and useful modifications thereof. Accordingly, aspects of the present description may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.), or by a combination of hardware and software. The above hardware or software may be referred to as a "data block," module, "" engine, "" unit, "" component, "or" system. Furthermore, aspects of the specification may take the form of a computer product, comprising computer-readable program code, embodied in one or more computer-readable media.

The computer storage medium may contain a propagated data signal with the computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer storage medium may be any computer readable medium that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer storage medium may be propagated through any suitable medium, including radio, cable, fiber optic cable, RF, or the like, or a combination of any of the foregoing.

The computer program code necessary for operation of portions of the present description may be written in any one or more programming languages, including an object oriented programming language such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python and the like, a conventional programming language such as C language, visual Basic, fortran2003, perl, COBOL2002, PHP, ABAP, a dynamic programming language such as Python, ruby and Groovy, or other programming languages and the like. The program code may execute entirely on the user's computer or as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or processing device. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or the use of services such as software as a service (SaaS) in a cloud computing environment.

Furthermore, the order in which the elements and sequences are processed, the use of numerical letters, or other designations in the description are not intended to limit the order in which the processes and methods of the description are performed unless explicitly recited in the claims. While certain presently useful inventive embodiments have been discussed in the foregoing disclosure, by way of various examples, it is to be understood that such details are merely illustrative and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements included within the spirit and scope of the embodiments of the present disclosure. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing processing device or mobile device.

Likewise, it should be noted that in order to simplify the presentation disclosed in this specification and thereby aid in understanding one or more inventive embodiments, various features are sometimes grouped together in a single embodiment, figure, or description thereof. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the present description. Indeed, less than all of the features of a single embodiment disclosed above.

In some embodiments, numbers describing the components, number of attributes are used, it being understood that such numbers being used in the description of embodiments are modified in some examples by the modifier "about," approximately, "or" substantially. Unless otherwise indicated, "about," "approximately," or "substantially" indicate that the number allows for a 20% variation. Accordingly, in some embodiments, numerical parameters set forth in the specification and claims are approximations that may vary depending upon the desired properties sought to be obtained by the individual embodiments. In some embodiments, the numerical parameters should take into account the specified significant digits and employ a method for preserving the general number of digits. Although the numerical ranges and parameters set forth herein are approximations that may be employed in some embodiments to confirm the breadth of the range, in particular embodiments, the setting of such numerical values is as precise as possible.

Each patent, patent application publication, and other material, such as articles, books, specifications, publications, documents, etc., referred to in this specification is incorporated herein by reference in its entirety. Except for application history documents that are inconsistent or conflicting with the content of this specification, documents that are currently or later attached to this specification in which the broadest scope of the claims to this specification is limited are also. It is noted that, if the description, definition, and/or use of a term in an attached material in this specification does not conform to or conflict with what is described in this specification, the description, definition, and/or use of the term in this specification controls.

Finally, it should be understood that the embodiments described in this specification are merely illustrative of the principles of the embodiments of this specification. Other variations are possible within the scope of this description. Thus, by way of example, and not limitation, alternative configurations of embodiments of the present specification may be considered as consistent with the teachings of the present specification. Accordingly, the embodiments of the present specification are not limited to only the embodiments explicitly described and depicted in the present specification.

Claims

A vehicle monitoring method, comprising:

acquiring operation condition data of a part to be detected of a vehicle, wherein the operation condition data at least comprise a plurality of groups of normal data sets under normal conditions, and each group of normal data sets comprises first operation data and first motion data of the vehicle at a moment corresponding to the first operation data;

acquiring at least one group of actual measurement data sets of the part to be detected in actual operation, wherein each group of actual measurement data sets comprises second operation data and second motion data of the vehicle at the moment corresponding to the second operation data; wherein, the first operation data and the second operation data both reflect the operation state information of the part to be detected, and the first movement data and the second movement data both reflect the movement state information of the vehicle;

And determining the running state of the part to be detected reflected by each group of measured data sets based on the running condition data and the measured data sets.
The method of claim 1, wherein the determining the operating state of the component to be detected reflected by each set of the measured data sets based on the operating condition data and the measured data sets comprises:

based on the plurality of groups of normal data sets, determining a normal data interval of the first operation data corresponding to each piece of first motion data;

based on the actual measurement data set and the normal data interval, when the first motion data and the second motion data are determined to be the same, comparing second operation data corresponding to the second motion data with the normal data interval corresponding to the first motion data, and obtaining a comparison result;

and determining the running state of the part to be detected based on the comparison result.
The method of claim 1, wherein the operating condition data further comprises an abnormal dataset during an abnormal condition, and wherein determining the operating condition of the component to be detected reflected by each set of the measured dataset based on the operating condition data and the measured dataset comprises:

Acquiring abnormal data sets of the part to be detected under the abnormal working condition, wherein each group of abnormal data sets comprises third operation data and third motion data of the vehicle at the moment corresponding to the third operation data; wherein the third operation data reflects the operation state information of the part to be detected, and the third movement data reflects the movement state information of the vehicle;

taking the normal data set as a positive sample, taking the abnormal data set as a negative sample, and training an initial first machine learning model by using the positive sample and the negative sample to obtain a trained first machine learning model;

and based on the actual measurement data sets, determining whether the operation state of the part to be detected reflected by each group of actual measurement data sets is normal or abnormal by using the first machine learning model after training.
The method of claim 3, wherein each of the normal data sets further includes first external data of the vehicle at a time corresponding to the first operating data, each of the abnormal data sets further includes second external data of the vehicle at a time corresponding to the third operating data, each of the first external data and the second external data reflecting operating environment information of the vehicle;

The taking the normal data set as a positive sample and the abnormal data set as a negative sample comprises the following steps:

taking the normal data set corresponding to the first external data in a first preset interval as a positive sample;

and taking the abnormal data set corresponding to the second external data in a second preset interval as a negative sample.
The method of claim 4, wherein the component to be detected comprises an electric motor, each of the first external data and the second external data comprises at least a road grade value and/or a vehicle load, each of the first operational data, the second operational data, and the third operational data comprises at least a current value of the electric motor, and each of the first motion data, the second motion data, and the third motion data comprises at least a travel speed of the vehicle.
The method of claim 1, wherein the operating condition data further includes a plurality of sets of aging data for an aging condition, a plurality of sets of data to be maintained for a maintenance condition, and determining an operating state of the component to be detected reflected by each set of the measured data sets based on the operating condition data and the measured data sets comprises:

Acquiring a plurality of groups of aging data sets of the part to be detected under the aging working condition, wherein each group of aging data sets comprises fourth operation data and fourth motion data of the vehicle at the moment corresponding to the fourth operation data;

acquiring a plurality of groups of to-be-maintained data sets of the to-be-detected component under the to-be-maintained working condition, wherein each group of to-be-maintained data sets comprises fifth operation data and fifth motion data of the vehicle at the moment corresponding to the fifth operation data; wherein the fourth operation data and the fifth operation data both reflect the operation state information of the component to be detected, and the fourth movement data and the fifth movement data both reflect the movement state information of the vehicle;

taking the normal data set, the aging data set and the data set to be maintained as training samples, and training an initial second machine learning model to obtain a trained second machine learning model;

based on the measured data sets, using the trained second machine learning model, determining whether the operating state of the component to be detected reflected by each set of measured data sets is normal, aged or to be repaired.
The method of claim 6, wherein training an initial machine learning model using the normal data set, the aged data set, and the data set to be serviced as training samples comprises:

and taking the normal data set, the ageing data set and the data set to be maintained as training samples, and training the initial machine learning model by using a preset algorithm.
The method of claim 1, wherein said acquiring at least one set of measured data sets of the part to be inspected in actual operation comprises:

determining the acquisition interval duration of the actual measurement data set according to the type of the part to be detected;

and acquiring each group of measured data sets at intervals of the acquisition interval duration.
A vehicle monitoring device, the device comprising:

the first acquisition module is used for acquiring operation condition data of a part to be detected of the vehicle, wherein the operation condition data at least comprise a plurality of groups of normal data sets under normal conditions, and each group of normal data sets comprises first operation data and first motion data of the vehicle at a moment corresponding to the first operation data;

the second acquisition module is used for acquiring at least one group of actual measurement data sets of the part to be detected in actual operation, wherein each group of actual measurement data sets comprises second operation data and second motion data of the vehicle at the moment corresponding to the second operation data; wherein, the first operation data and the second operation data both reflect the operation state information of the part to be detected, and the first movement data and the second movement data both reflect the movement state information of the vehicle;

And the state determining module is used for determining the operation state of the part to be detected reflected by each group of the actual measurement data sets based on the operation condition data and the actual measurement data sets.
The apparatus of claim 9, wherein the status determination module is to:

based on the plurality of groups of normal data sets, determining a normal data interval of the first operation data corresponding to each piece of first motion data;

based on the actual measurement data set and the normal data interval, when the first motion data and the second motion data are determined to be the same, comparing second operation data corresponding to the second motion data with the normal data interval corresponding to the first motion data, and obtaining a comparison result;

and determining the running state of the part to be detected based on the comparison result.
The apparatus of claim 9, wherein the operating condition data further comprises an abnormal data set during an abnormal condition, the state determination module to:

acquiring abnormal data sets of the part to be detected under the abnormal working condition, wherein each group of abnormal data sets comprises third operation data and third motion data of the vehicle at the moment corresponding to the third operation data; wherein the third operation data reflects the operation state information of the part to be detected, and the third movement data reflects the movement state information of the vehicle;

Taking the normal data set as a positive sample, taking the abnormal data set as a negative sample, and training an initial first machine learning model by using the positive sample and the negative sample to obtain a trained first machine learning model;

and based on the actual measurement data sets, determining whether the operation state of the part to be detected reflected by each group of actual measurement data sets is normal or abnormal by using the first machine learning model after training.
The apparatus of claim 11, wherein each set of the normal data further comprises first external data of the vehicle at a time corresponding to the first operational data, each set of the abnormal data further comprises second external data of the vehicle at a time corresponding to the third operational data, each of the first external data and the second external data reflecting operational environmental information of the vehicle;

the taking the normal data set as a positive sample and the abnormal data set as a negative sample comprises the following steps:

taking the normal data set corresponding to the first external data in a first preset interval as a positive sample;

and taking the abnormal data set corresponding to the second external data in a second preset interval as a negative sample.
The apparatus of claim 12, wherein the component to be detected comprises a motor, each of the first external data and the second external data comprises at least a road grade value and/or a vehicle load, each of the first operational data, the second operational data, and the third operational data comprises at least a current value of the motor, and each of the first motion data, the second motion data, and the third motion data comprises at least a travel speed of the vehicle.
The apparatus of claim 9, wherein the operating condition data further comprises a plurality of sets of aging data for an aging condition, a plurality of sets of data to be maintained for a maintenance condition, the status determination module to:

acquiring a plurality of groups of aging data sets of the part to be detected under the aging working condition, wherein each group of aging data sets comprises fourth operation data and fourth motion data of the vehicle at the moment corresponding to the fourth operation data;

acquiring a plurality of groups of to-be-maintained data sets of the to-be-detected component under the to-be-maintained working condition, wherein each group of to-be-maintained data sets comprises fifth operation data and fifth motion data of the vehicle at the moment corresponding to the fifth operation data; wherein the fourth operation data and the fifth operation data both reflect the operation state information of the component to be detected, and the fourth movement data and the fifth movement data both reflect the movement state information of the vehicle;

Taking the normal data set, the aging data set and the data set to be maintained as training samples, and training an initial second machine learning model to obtain a trained second machine learning model;

based on the measured data sets, using the trained second machine learning model, determining whether the operating state of the component to be detected reflected by each set of measured data sets is normal, aged or to be repaired.
The apparatus of claim 14, wherein training an initial machine learning model using the normal data set, the aged data set, and the data set to be serviced as training samples comprises:

and taking the normal data set, the ageing data set and the data set to be maintained as training samples, and training the initial machine learning model by using a preset algorithm.
The apparatus of claim 9, wherein the second acquisition module is to:

determining the acquisition interval duration of the actual measurement data set according to the type of the part to be detected;

and acquiring each group of measured data sets at intervals of the acquisition interval duration.
A vehicle monitoring device comprising at least one storage medium for storing computer instructions and at least one processor; the at least one processor is configured to execute the computer instructions to implement the method of any one of claims 1-8.
A computer readable storage medium storing computer instructions which, when read by a computer in the storage medium, perform the method of any one of claims 1 to 8.