CN115798078A - Vehicle accurate fault diagnosis method and device - Google Patents
Vehicle accurate fault diagnosis method and device Download PDFInfo
- Publication number
- CN115798078A CN115798078A CN202211514082.2A CN202211514082A CN115798078A CN 115798078 A CN115798078 A CN 115798078A CN 202211514082 A CN202211514082 A CN 202211514082A CN 115798078 A CN115798078 A CN 115798078A
- Authority
- CN
- China
- Prior art keywords
- vehicle
- fault
- failure
- data
- sample data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/60—Other road transportation technologies with climate change mitigation effect
- Y02T10/70—Energy storage systems for electromobility, e.g. batteries
Landscapes
- Vehicle Cleaning, Maintenance, Repair, Refitting, And Outriggers (AREA)
Abstract
The invention discloses a vehicle accurate fault diagnosis method and a vehicle accurate fault diagnosis device, wherein the method comprises the following steps: acquiring the residual capacity of a vehicle battery; judging whether the residual electric quantity is smaller than a first preset value or not; the vehicle-mounted central control acquires the actual unlocking times of the vehicle within a preset time period; judging whether the difference value between the number of times of receiving the unlocking command and the actual unlocking number within a preset time period is greater than a second preset value or not; and acquiring sample data of the vehicle, determining a vehicle portrait, inputting the vehicle portrait into a training model, and outputting a fault type. The invention detects the function of each part of the vehicle based on a plurality of sensors of the vehicle, inputs the function to a fault detection model trained in advance by matching with other basic data and use data, detects the fault and confirms whether the vehicle is a fault vehicle. In addition, the Bluetooth module is adopted to assist the communication module in information transmission, so that fault information can be effectively reflected timely and accurately, and user experience is improved.
Description
Technical Field
The invention belongs to the technical field of power-assisted vehicles, and particularly relates to a vehicle accurate fault diagnosis method and device.
Background
With the continuous development of the shared vehicle industry such as the shared bicycle and the moped industry, the shared bicycle and the moped are distributed all over the country. On the aspect of solving the problem of short trip, travelers increasingly rely on a shared traffic trip mode, and the supply of shared bicycles/mopeds is increased. However, when the number of vehicles reaches a certain number, the failure rate of the vehicles starts to rise along with the increase of the use times and time of the vehicles, the riding experience of users is directly influenced by the vehicle failure, even potential safety hazards exist, and meanwhile the workload of vehicle operation and maintenance personnel is increased. Especially, the shared moped is provided with electric components such as a storage battery and an auxiliary motor, so that the types of faults are increased greatly.
The existing shared vehicles are usually reported passively after a fault occurs, or operation and maintenance personnel detect whether the vehicle has a fault in the field. The vehicle actively reports the fault, which usually can only report some systematic problems, for example, the vehicle cannot be unlocked, the vehicle power is low, and many faults are suspected faults and are not real faults, so that the fault reporting accuracy is low; and the operation and maintenance personnel need to detect a large number of vehicles in an overlaying manner when detecting the vehicle faults on the spot, so that a large amount of labor cost is consumed, and the timeliness of fault detection is difficult to guarantee. In addition, when the vehicle positioning module and/or the communication module do not work, the vehicle cannot actively report fault information, so that the available vehicles at the station are insufficient, and the borrowing and traveling of the user are influenced.
In view of the above defects, the technical problems to be solved by the present invention are that the vehicle fault reporting rate is low or the fault feedback is not timely, inaccurate or even impossible in the prior art.
Disclosure of Invention
In order to overcome the technical defects, the invention provides a vehicle accurate fault diagnosis method and a vehicle accurate fault diagnosis device, which aim to solve the problems related to the background technology.
The invention provides a vehicle accurate fault diagnosis method and a device, comprising the following steps:
the vehicle-mounted central control acquires the residual electric quantity of a vehicle battery; judging whether the residual electric quantity is smaller than a first preset value or not; if yes, outputting the fault type of the low-electricity vehicle, and informing operation and maintenance personnel; if not, executing the next step;
the vehicle-mounted central control acquires the actual unlocking times of the vehicle within a preset time period; judging whether the difference value between the number of times of receiving the unlocking command and the actual unlocking number within a preset time period is greater than a second preset value or not; if yes, outputting the fault type as an unlocking overtime fault vehicle, and notifying operation and maintenance personnel; if not, executing the next step;
the vehicle-mounted central control acquires sample data of the vehicle and transmits the sample data to the background server; the sample data comprises a plurality of dimension information related to the vehicle riding state and a fault label for marking a fault vehicle;
the background server determines a vehicle portrait of the vehicle based on the sample data, inputs the vehicle portrait into a training model and outputs a fault type; and the training model is a fault recognition model obtained by weighting the vehicle portrait processed by the machine learning model and the corresponding fault label.
Preferably or optionally, the dimension information comprises: and detecting the running state of each part of the vehicle.
Preferably or optionally, the detection data of the operating states of the parts of the vehicle comprises: the vehicle-mounted brake system comprises a vehicle riding speed, a pedal output torque, a motor output torque, a battery output voltage, a battery temperature, a brake pressure and a brake distance.
Preferably or optionally, the dimension information comprises: the system comprises detection data of the running state of each part of the vehicle, basic attribute data of the vehicle, historical fault and maintenance data and historical riding data of the vehicle.
Preferably or optionally, the detection data of the operating states of the parts of the vehicle comprises: the method comprises the following steps of (1) vehicle riding speed, pedal output torque, motor output torque, battery output voltage, battery temperature, brake pressure and brake distance;
the vehicle base attribute data includes: the method comprises the following steps of (1) carrying out delivery batch of vehicles, the operation time of the vehicles, the operation area of the vehicles, and the order condition and the order cancellation amount in the latest period of time;
the vehicle historical failure and maintenance data includes: historical fault conditions and maintenance conditions of the vehicle within a preset time period;
the historical riding data of the vehicle comprises: historical average travel time, historical average travel speed, historical average travel distance, and historical operating history.
Preferably or optionally, before inputting the vehicle representation into a training model, the diagnostic method further comprises the steps of:
judging whether the boosting ratio of the vehicle exceeds a preset range for a plurality of times within a preset time period; the assist ratio is = motor output torque/pedal torque;
if the vehicle portrait is higher than the maximum value of the preset range, inputting the vehicle portrait into different first training models, and if the vehicle portrait is lower than the minimum value of the preset range, inputting the vehicle portrait into different first training models; the first training model is obtained based on vehicle portrayal and first fault type training; the second training model is trained based on the vehicle representation and a second fault type.
Preferably or optionally, the first fault type comprises: power failure, motor failure, controller failure, control device failure;
the second fault type includes: pedal failure, transmission failure, brake failure, wheel and accessory failure, handle failure, vehicle sway or abnormal sound.
Preferably or optionally, the method for the vehicle-mounted central control to transmit the sample data to the background server comprises the following steps:
judging whether the communication module is connected with a background server or not; if yes, transmitting the sample data to a background server through a communication module; if not, executing the next step;
broadcasting request assistance information through the Bluetooth module until the Bluetooth module on the adjacent vehicle or the parking equipment responds, and transmitting the request assistance information to the Bluetooth transmitter of the vehicle to be detected;
transmitting the sample data to a Bluetooth module on an adjacent vehicle or parking device through the Bluetooth module;
and transmitting the sample data of the vehicle to be detected to the background server through the communication module on the adjacent vehicle or the parking pile.
In a third aspect, the present invention further provides a system based on the vehicle precision fault diagnosis method, including:
a first acquisition unit configured to acquire a remaining capacity of a vehicle battery;
a first determination unit configured to determine whether the remaining power is less than a first preset value; if yes, outputting the fault type of the low-electricity vehicle, and informing operation and maintenance personnel; if not, executing the next step;
the second acquisition unit is configured to acquire the actual unlocking times of the vehicle within a preset time period by the vehicle-mounted central control;
the second judging unit is configured to judge whether the difference value between the number of times of receiving the unlocking command and the actual unlocking number within the preset time period is greater than a second preset value; if yes, outputting the fault type as an unlocking overtime fault vehicle, and notifying operation and maintenance personnel; if not, executing the next step;
the third acquisition unit is configured to acquire the sample data of the vehicle and transmit the sample data to the background server; the sample data comprises a plurality of dimension information related to the vehicle riding state and a fault label for marking a fault vehicle;
a first processing unit configured to determine a vehicle representation of the vehicle based on the sample data, input the vehicle representation into a training model, and output a fault type; and the training model is a fault recognition model obtained by weighting the vehicle portrait processed by the machine learning model and the corresponding fault label.
In a third aspect, the present invention is also a server for vehicle precise fault diagnosis, including a memory, a processor, and a computer program stored in the memory and operable on the processor, wherein the processor implements the steps of the method when executing the program.
The invention relates to a vehicle accurate fault diagnosis method and a device, compared with the prior art, the vehicle accurate fault diagnosis method and the device have the following beneficial effects:
1. according to the invention, the function detection is carried out on each part of the vehicle based on a plurality of sensors of the vehicle, and other basic data and use data are matched and input into a fault detection model trained in advance to carry out fault detection, whether the vehicle is a fault vehicle is confirmed, and even which vehicles have a fault tendency can be effectively judged, so that the problems of low vehicle fault reporting rate or untimely and inaccurate fault feedback in the prior art are avoided.
2. The various data obtained in the invention can directly use the detection function before the equipment without adding other sensors and detection equipment, thereby reducing the operation cost of the whole diagnosis method.
3. According to the invention, a proper pre-classification mode is designed according to the types of defects, the detection precision is ensured, the detection efficiency is improved, and more than 95% of faulty vehicles can be detected according to experiments.
4. The invention adopts the mode of temporarily storing data in the memory, records sample data, and then regularly exchanges data, thereby ensuring the reliability of data transmission, avoiding occupying a large amount of bandwidth, and also reducing the operation cost.
Drawings
Fig. 1 is a schematic flowchart of a vehicle accurate fault diagnosis method in embodiment 1 of the present invention.
Fig. 2 shows a vehicle precision fault diagnosis apparatus in embodiment 2 of the present invention.
Fig. 3 is a schematic structural diagram of an exemplary electronic device in embodiment 3 of the present invention.
Description of reference numerals: a first acquiring unit 11, a first judging unit 12, a second acquiring unit 13, a second judging unit 14, a third acquiring unit 15, a first processing unit 16, a bus 300, a receiver 301, a processor 302, a transmitter 303, a memory 304, and a bus interface 305.
Detailed Description
In the following description, numerous specific details are set forth in order to provide a more thorough understanding of the present invention. It will be apparent, however, to one skilled in the art, that the present invention may be practiced without one or more of these specific details. In other instances, well-known features have not been described in order to avoid obscuring the invention.
Example 1
Referring to fig. 1, a method for accurately diagnosing a fault of a vehicle includes:
s100, acquiring the residual electric quantity of a vehicle battery by vehicle-mounted central control; judging whether the residual electric quantity is smaller than a first preset value or not; if yes, outputting the fault type of the low-power vehicle, and notifying operation and maintenance personnel; if not, executing the next step;
specifically, the vehicle mainly refers to a shared moped, the battery residual capacity can be acquired through a battery sensor arranged on the shared moped, the battery sensor is connected with a central control panel of the shared moped, in the implementation process, the residual capacity information of the battery can be directly acquired through the central control panel, the first preset capacity is the lowest value of the battery residual capacity arranged for ensuring the safety of the battery, and the first preset capacity is determined by the characteristics of a rechargeable battery on the shared moped and is generally determined according to the relevant parameters of the rechargeable battery.
It is understood that the battery may be a rechargeable battery, but is not limited to a rechargeable battery, and it is also known to those skilled in the art that the battery may be a fuel cell, and the residual ionization of the fuel cell is confirmed by detecting the residual hydrogen content in the hydrogen storage device. For convenience of description, the following description will be given by taking a rechargeable battery as an example.
S200, acquiring the actual unlocking times of the vehicle within a preset time period by vehicle-mounted central control; judging whether the difference value between the number of times of receiving the unlocking command and the actual unlocking number within a preset time period is greater than a second preset value or not; if yes, outputting the fault type as an unlocking overtime fault vehicle, and informing operation and maintenance personnel; if not, executing the next step;
specifically, the user unlocks through the two-dimensional code of scanning automobile body, the system sends the instruction of unblanking, the tool to lock execution of sharing vehicle using motor unlocks the order, give the system feedback after unblanking the completion, for once complete action of unblanking, if the system does not receive feedback information in certain time, then can carry out the action of unblanking again, do not receive the tool to lock feedback in scheduled time, if the vehicle unblank in the time of predetermineeing in succession when the timeout number of times exceeds the predetermined threshold value, the threshold value generally sets up to be greater than or equal to 3 times in succession, and can regard as the failure of unblanking, and can mark as tool to lock trouble vehicle.
S300, acquiring vehicle sample data by a vehicle-mounted central control, and transmitting the vehicle sample data to a background server; the sample data comprises a plurality of dimension information related to the vehicle riding state and a fault label for marking a fault vehicle;
specifically, rules are found in the characteristic parameter data of each part of the vehicle, and relevant data which are relatively high in relevance with the fault vehicle and easy to judge the fault vehicle are found. In other words, obvious characterization differences exist on the dimension information of the fault vehicle and the non-fault vehicle at the relevant latitudes, and the differences among the characterization data are mined, so that whether the shared moped is a fault vehicle can be reversely confirmed, even which shared moped has a fault tendency can be effectively judged, maintenance is timely carried out, further deterioration of a fault area is avoided, and the operation cost is reduced.
In a preferred embodiment, the sample data comprises: the detection data of the running state of each part of the vehicle and a fault label for marking the fault vehicle.
Wherein, the detection data of each part running state of vehicle includes: the vehicle running speed, the pedal output torque, the motor output torque, the battery output voltage, the battery temperature, the brake pressure, the brake distance and other parameters. The riding speed of the vehicle is detected by a distance measuring sensor arranged on the shared moped, and in addition, the riding speed of the vehicle can also be directly detected by a positioning system of the shared moped, although a certain deviation exists, the riding speed of the vehicle is within an allowable range, generally about 1-2 kilometers per hour, and the riding speed of the vehicle can be ignored for the whole calculation mode. The pedal compression force is measured through array pedal output torque arranged on two sides of the pedal and motor output torque through rotating speed sensors arranged at the pedal and the motor; the output voltage and the temperature of the battery are obtained by a voltage detection device and a temperature sensor which are arranged on the battery; the brake pressure is detected by a brake sensor which is arranged in the drum brake and used for detecting the moving distance of the piston or the pressure change condition between the piston and the hub, and the brake distance is measured by matching a distance measuring sensor and the brake sensor. The acquisition of each parameter can directly follow the sensor and the detection equipment on the existing shared moped, and in the implementation process, the data are only required to be relatively integrated and summarized without newly adding the sensor and the detection equipment, so that the operation cost of the whole diagnosis method is reduced.
The trouble ticket for marking a trouble vehicle includes: battery failure, motor failure, controller failure, control transmission line failure, pedal failure, transmission failure, brake failure, wheel and accessory failure, handle failure, vehicle sway or abnormal sound.
The detection data of the running states of all parts of the vehicle and fault labels for marking fault vehicles are integrated, for example, under the condition that the riding speed is basically kept consistent, when a battery has a fault, the output voltage of the battery is reduced, the temperature of the battery is increased, the output torque of a motor is reduced, and the torque of a pedal is increased; when the transmission device fails, the output torque of the pedal is increased, and the output torque of the motor is increased; when the braking device fails, the braking pressure is reduced and the motor output torque is increased in comparison with the standard braking pressure and the standard motor output torque in the braking process. When different types of faults occur, the detection data of the running states of one or more parts of the vehicle can fluctuate, and by mining the difference between the characterization data, whether the shared moped is a fault vehicle can be reversely confirmed, and even which shared moped has a fault tendency can be effectively judged.
In another preferred embodiment, the sample data comprises: the system comprises detection data of the running state of each part of the vehicle, basic attribute data of the vehicle, historical fault and maintenance data, historical riding data of the vehicle and fault labels for marking the faulty vehicle.
The detection data of the running states of the parts of the vehicle and the fault label for marking the fault vehicle are the same as those of the preferred embodiment, and are not described herein again.
The vehicle base attribute data includes: the vehicle dispatching batch, the vehicle operation time, the vehicle operation area, the order condition and the order cancellation amount condition in the latest period of time. The specific similarity of parts leaving the factory in the same batch also shows certain similarity after being integrated into a whole vehicle, in addition, a fault vehicle usually can be piled up, namely, the road condition of a use area also has certain influence on the occurrence of faults, therefore, the operation area for extracting the vehicle can also provide corresponding information for fault identification, and the data mining also proves the point. The higher the order quantity in the last period of time is, the higher the abrasion to the vehicle is relatively, the higher the probability of failure is, the higher the order cancellation quantity in the last period of time is, the lower the riding performance of the shared moped by the user is satisfactory enough, the higher the order cancellation quantity in the last period of time is, the lower the riding performance of the shared moped by the user is, the higher the order cancellation quantity in the last period of time is, the lower the order cancellation quantity in the last period of time is, the shared moped is determined by comprehensively considering factors such as weather, operation area and pedestrian flow. Therefore, the extraction of the delivery lot of the vehicle, the operation time of the vehicle, the operation area of the vehicle, the order condition and the order cancellation amount condition in the preset time can also provide corresponding information for fault identification, and the data mining also proves the problem.
The vehicle historical failure and maintenance data includes: historical fault conditions and maintenance conditions of the vehicle within a preset time period; generally speaking, the failure of the vehicle has a certain periodicity within a certain range, and due to the problem of running-in between parts, the vehicle is more likely to fail again after the failure, especially for some high-frequency failure vehicles. Therefore, the representation of the health dimension of the vehicle can be established by advancing relevant data of historical faults, maintenance times, historical fault parts and the like of the vehicle.
The historical riding data of the vehicle comprises: historical average travel time, historical average travel speed, historical average travel distance, and historical operating history. It is understood that the usage pattern and usage habit of the vehicle are closely related to the possibility of the vehicle being in failure, so the present embodiment infers the possibility of the vehicle being in failure by recording the historical operation records of the vehicle, which can obtain the usage information of the braking frequency, the steering curvature, the braking of the front and/or rear braking devices, the over-exertion of the pedal, and the like when the user uses the vehicle, through the rotation sensors provided at the handlebars, the braking pressure, the pedal output torque, and the like. In addition. The historical average running duration, the historical average running speed, the historical average running distance and the like are expanded, the related riding information is extracted to serve as data characteristics, the characteristics of the vehicle in the riding dimension are supplemented, and the image of the vehicle in the riding dimension is richer.
S400, acquiring a power assisting ratio of the vehicle in a preset time period; judging whether the vehicle has a fault or not and judging the fault type of the fault vehicle;
in order to improve the recognition efficiency and recognition accuracy of the whole training model, the fault types are pre-classified before the determined portrait is input into the training model. The shared moped comprises an electric power-assisted driving system and a bicycle system. The common fault of the electric power-assisted driving system corresponds to a first fault type, and specifically comprises the following steps: power failure, motor failure, controller failure, control device failure. Common faults of the bicycle system correspond to a second fault type, and specifically include: pedal failure, transmission failure, brake failure, wheel and accessory failure, handle failure, vehicle sway or abnormal sound.
The electric sharing power-assisted vehicle generally estimates the treading moment of a user during riding and controls the output torque of a power-assisted motor according to the estimated moment so as to realize the whole power-assisted process; during normal driving, motor torque is generally proportional to pedal torque, providing a greater motor output torque as the pedaling rate is higher. That is, in the case of the uniform running, the ratio between the motor output torque and the pedal torque of the electric shared power-assisted vehicle should be a constant value, that is, the power-assisted ratio is a constant value, which is defined as = motor output torque/pedal torque. Therefore, by comparing the resistance ratio at different speeds, if the assistance ratio is too large, it is indicated that the fault probability of the shared moped appears in the self-driving system, the weight of the first fault type can be properly increased, or a first training model obtained based on the first fault type training is adopted; if the boosting ratio is too low, the failure probability of the power vehicle is shown to be in the electric power-assisted driving system, and the weight of the second failure type can be properly increased or a second training model obtained based on the training of the second failure type is adopted.
S500, the background server determines the vehicle portrait of the vehicle based on the sample data, inputs the vehicle portrait into a training model and outputs a fault type; and the training model is a fault recognition model obtained by weighting the vehicle portrait processed by the machine learning model and the corresponding fault label.
The training model may be a model including a neural network, and is obtained by training a large amount of sample data. Specifically, the fault detection model may include a neural network composed of an input layer, a convolution layer, a pooling layer, an output layer, and the like, and the number of convolution kernels is set mainly according to an input feature type or a feature type to be analyzed, a basic network structure is constructed, training and learning are performed by using a training sample in a sample set, verification of prediction accuracy is performed by using a verification sample, and a final training process is completed under the condition that certain convergence is achieved, so that the fault detection model is obtained. It should be noted that, for the network structure in the fault detection model, it can be adjusted according to the input and output parameters, and those skilled in the art can set the basic model structure based on the input and output parameters given in the present embodiment based on the known existing neural network structure. The method mainly comprises the steps of analyzing and predicting whether the vehicle has faults or not by taking detection data of running states of all parts of the vehicle, basic attribute data of the vehicle, historical fault and maintenance data and historical riding data of the vehicle as input, and the corresponding specific model structure is not limited.
In a further embodiment, corresponding to step S400, the training models include a first training model and a second training model, the first training model being trained based on the vehicle representation and the first fault type; the second training model is obtained based on vehicle portraits and second fault types in a training mode, and when the vehicle portraits are obtained, a plurality of interference data in detection data of the running states of all parts of the vehicle can be eliminated according to the fault types, so that the processing rate of the whole training model is improved. When the first fault type is further judged, parameters such as braking pressure, braking distance and the like can be eliminated; when a further determination is made regarding the second fault type, parameters such as battery temperature may be rejected. Therefore, a proper pre-classification mode is designed according to the types of the defects, the detection precision is ensured, the detection efficiency is improved, and more than 95% of detection of the fault vehicles can be solved according to experiments.
It should be noted that, since the failure occurrence area (the failed shared power-assisted vehicle) and the failure analysis area (the backend server) are separated, how to perform effective information exchange becomes the key point of the entire failure detection method. When the vehicle positioning module and/or the communication module do not work, the vehicle cannot actively report fault information, so that the available vehicles at the station are insufficient, and the influence on vehicle borrowing and traveling of a user is caused. The applicant therefore proposes a data exchange method comprising the following steps: periodically polling the boosting ratio of the vehicle by an on-board central control; the assist ratio is = motor output torque/pedal torque; judging whether the boosting ratio of the vehicle exceeds a preset range for a plurality of times within a preset time period; if so, acquiring detection data of the running state of each part of the vehicle in the period of time in the memory to form sample data; the vehicle-mounted central control of the vehicle to be detected judges whether the vehicle-mounted communication module is connected with the background server or not; if so, transmitting the sample data to a background server through a communication module, wherein the communication module mainly refers to a wireless transmission device; if not, the vehicle-mounted wireless module is judged to have a fault, and the next step is executed; broadcasting request assistance information through the Bluetooth module until the Bluetooth module on the adjacent vehicle or the parking equipment responds, and transmitting the request assistance information to the Bluetooth transmitter of the vehicle to be detected; the Bluetooth module can be a Bluetooth transmitter arranged on a vehicle or a Bluetooth repeater arranged on a parking peg; transmitting the sample data to a Bluetooth module on an adjacent vehicle or parking device through the Bluetooth module; and transmitting the sample data of the vehicle to be detected to the background server through the communication module on the adjacent vehicle or the parking pile. The embodiment adopts the Bluetooth module to assist the communication module to transmit information, can timely and accurately effectively reflect fault information, and improves user experience. Wherein, bluetooth transmitter is a part of on-vehicle intelligence lock to improve hardware cost, but can further improve information transmission's stability, improve vehicle failure diagnosis's accuracy nature.
Example 2
Based on the same inventive concept as the vehicle precision fault diagnosis method in the foregoing embodiment 1, the present invention further provides a vehicle precision fault diagnosis apparatus, as shown in fig. 2, the apparatus includes:
a first acquisition unit 11 configured to acquire a remaining capacity of a vehicle battery;
a first judgment unit 12 configured to judge whether the remaining power is smaller than a first preset value; if yes, outputting the fault type of the low-electricity vehicle, and informing operation and maintenance personnel; if not, executing the next step;
the second obtaining unit 13 is configured to obtain the actual unlocking times of the vehicle within a preset time period through the vehicle-mounted central control;
a second judging unit 14 configured to judge whether a difference between the number of times of receiving the unlocking command and the actual number of times of unlocking within a preset time period is greater than a second preset value; if yes, outputting the fault type as an unlocking overtime fault vehicle, and notifying operation and maintenance personnel; if not, executing the next step;
a third acquiring unit 15 configured to acquire vehicle sample data including a plurality of dimensional information related to the vehicle riding state and a trouble tag for marking a trouble vehicle, and determine a vehicle representation;
a first processing unit 16 configured to input the vehicle representation into a training model, and output a fault type; and the training model is a fault recognition model obtained by weighting the vehicle portrait processed by the machine learning model and the corresponding fault label.
Various changes and specific examples of the vehicle precision fault diagnosis method in the foregoing embodiment 1 are also applicable to the vehicle precision fault diagnosis device in this embodiment, and through the foregoing detailed description of the vehicle precision fault diagnosis method, a person skilled in the art can clearly know the implementation method of the vehicle precision fault diagnosis device in this embodiment, so for the brevity of the description, detailed descriptions are omitted here.
Example 3
Based on the same inventive concept as one of the vehicle precision fault diagnosis methods in the foregoing embodiments, the present invention further provides a vehicle precision fault diagnosis server, as shown in fig. 3, where fig. 3 is an exemplary electronic device in embodiment 3, and includes a memory 304, a processor 302, and a computer program stored on the memory 304 and executable on the processor 302, and the processor 302 implements the steps of any one of the vehicle precision fault diagnosis methods when executing the program.
Wherein in fig. 3 a bus architecture (represented by bus 300), bus 300 may include any number of interconnected buses and bridges, bus 300 linking together various circuits including one or more processors, represented by processor 302, and memory, represented by memory 304. The bus 300 may also link together various other circuits such as peripherals, voltage regulators, power management circuits, and the like, which are well known in the art, and therefore, will not be described any further herein. A bus interface 305 provides an interface between the bus 300 and the receiver 301 and transmitter 303. The receiver 301 and the transmitter 303 may be the same element, i.e., a transceiver, providing a means for communicating with various other apparatus over a transmission medium.
The processor 302 is responsible for managing the bus 300 and general processing, and the memory 304 may be used for storing data used by the processor 302 in performing operations.
It should be noted that the various features described in the above embodiments may be combined in any suitable manner without departing from the scope of the invention. The invention is not described in detail in order to avoid unnecessary repetition.
Claims (10)
1. A vehicle precision fault diagnosis method is characterized by comprising the following steps:
the vehicle-mounted central control acquires the residual electric quantity of a vehicle battery; judging whether the residual electric quantity is smaller than a first preset value or not; if yes, outputting the fault type of the low-power vehicle, and notifying operation and maintenance personnel; if not, executing the next step;
the vehicle-mounted central control acquires the actual unlocking times of the vehicle within a preset time period; judging whether the difference value between the number of times of receiving the unlocking command and the actual unlocking number within a preset time period is greater than a second preset value or not; if yes, outputting the fault type as an unlocking overtime fault vehicle, and notifying operation and maintenance personnel; if not, executing the next step;
the vehicle-mounted central control acquires sample data of the vehicle and transmits the sample data to the background server; the sample data comprises a plurality of dimension information related to the vehicle riding state and a fault label for marking a fault vehicle;
the background server determines a vehicle portrait of the vehicle based on the sample data, inputs the vehicle portrait into a training model and outputs a fault type; and the training model is a fault recognition model obtained by weighting the vehicle portrait processed by the machine learning model and the corresponding fault label.
2. The vehicle precision fault diagnosis method according to claim 1, wherein the dimension information includes: and detecting the running state of each part of the vehicle.
3. The vehicle precision fault diagnosis method according to claim 1, wherein the detection data of the operation states of the vehicle parts comprises: the vehicle-mounted brake system comprises a vehicle riding speed, a pedal output torque, a motor output torque, a battery output voltage, a battery temperature, a brake pressure and a brake distance.
4. The vehicle precision fault diagnosis method according to claim 1, wherein the dimension information includes: the method comprises the following steps of detecting data of the running state of each part of the vehicle, basic attribute data of the vehicle, historical fault and maintenance data and historical riding data of the vehicle.
5. The vehicle precision fault diagnosis method according to claim 4, wherein the detection data of the operation states of the vehicle parts comprises: the method comprises the following steps of (1) vehicle riding speed, pedal output torque, motor output torque, battery output voltage, battery temperature, brake pressure and brake distance;
the vehicle base attribute data includes: the method comprises the following steps of (1) carrying out delivery batch of vehicles, the operation time of the vehicles, the operation area of the vehicles, and the order condition and the order cancellation amount in the latest period of time;
the vehicle historical failure and maintenance data includes: historical fault conditions and maintenance conditions of the vehicle within a preset time period;
the historical riding data of the vehicle comprises: historical average travel time, historical average travel speed, historical average travel distance, and historical operating history.
6. The vehicle precision fault diagnosis method according to claim 1, wherein before the vehicle representation is input into a training model, the diagnosis method further comprises the following steps:
judging whether the boosting ratio of the vehicle exceeds a preset range for multiple times within a preset time period; the assist ratio is = motor output torque/pedal torque;
if the vehicle portrait is higher than the maximum value of the preset range, inputting the vehicle portrait into different first training models, and if the vehicle portrait is lower than the minimum value of the preset range, inputting the vehicle portrait into different first training models; the first training model is obtained based on vehicle portrayal and first fault type training; the second training model is trained based on the vehicle representation and a second fault type.
7. The vehicle precision fault diagnosis method according to claim 6, wherein the first fault type includes: power failure, motor failure, controller failure, control device failure;
the second fault type includes: pedal failure, transmission failure, brake failure, wheel and accessory failure, handle failure, vehicle sway or abnormal sound.
8. The vehicle precision fault diagnosis method according to claim 1, wherein the method for the vehicle central control to transmit the sample data to the background server comprises the following steps:
judging whether the communication module is connected with a background server or not; if yes, transmitting the sample data to a background server through a communication module; if not, executing the next step;
broadcasting request assistance information through the Bluetooth module until the Bluetooth module on the adjacent vehicle or the parking equipment responds and is connected with the Bluetooth transmitter of the vehicle to be detected;
transmitting the sample data to a Bluetooth module on an adjacent vehicle or parking device through the Bluetooth module;
and transmitting the sample data of the vehicle to be detected to the background server through the communication module on the adjacent vehicle or the parking pile.
9. A diagnosis device based on the vehicle precision fault diagnosis method according to any one of claims 1 to 8, characterized by comprising:
a first acquisition unit configured to acquire a remaining capacity of a vehicle battery;
a first judgment unit configured to judge whether the remaining power is less than a first preset value; if yes, outputting the fault type of the low-power vehicle, and notifying operation and maintenance personnel; if not, executing the next step;
the second acquisition unit is configured to acquire the actual unlocking times of the vehicle in a preset time period by the vehicle-mounted central control unit;
the second judging unit is configured to judge whether the difference value between the number of times of receiving the unlocking command and the actual unlocking number of times in the preset time period is larger than a second preset value; if yes, outputting the fault type as an unlocking overtime fault vehicle, and informing operation and maintenance personnel; if not, executing the next step;
the third acquisition unit is configured to acquire the sample data of the vehicle and transmit the sample data to the background server; the sample data comprises a plurality of dimension information related to the vehicle riding state and a fault label for marking a fault vehicle;
a first processing unit configured to determine a vehicle representation of the vehicle based on the sample data, input the vehicle representation into a training model, and output a fault type; and the training model is a fault recognition model obtained by weighting the vehicle portrait processed by the machine learning model and the corresponding fault label.
10. A server for vehicle precision fault diagnosis, comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor executes the program to implement the steps of the method according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211514082.2A CN115798078A (en) | 2022-11-29 | 2022-11-29 | Vehicle accurate fault diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211514082.2A CN115798078A (en) | 2022-11-29 | 2022-11-29 | Vehicle accurate fault diagnosis method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115798078A true CN115798078A (en) | 2023-03-14 |
Family
ID=85443267
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211514082.2A Pending CN115798078A (en) | 2022-11-29 | 2022-11-29 | Vehicle accurate fault diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115798078A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881980A (en) * | 2020-07-29 | 2020-11-03 | 上海钧正网络科技有限公司 | Vehicle fault detection method and device, computer equipment and storage medium |
| CN116466689A (en) * | 2023-06-19 | 2023-07-21 | 广汽埃安新能源汽车股份有限公司 | Fault diagnosis method and device |
| CN116778717A (en) * | 2023-08-10 | 2023-09-19 | 浙江小遛信息科技有限公司 | Fault identification method and server for shared vehicle |
| CN117104377A (en) * | 2023-10-23 | 2023-11-24 | 西安小果出行科技有限公司 | Intelligent management system and method for electric bicycle |
| CN117135686A (en) * | 2023-10-24 | 2023-11-28 | 深圳市蓝鲸智联科技股份有限公司 | Bluetooth-based vehicle-mounted information interaction method and system |
| CN117172756A (en) * | 2023-11-01 | 2023-12-05 | 深圳市信润富联数字科技有限公司 | Mold management method, apparatus, device and storage medium |
-
2022
- 2022-11-29 CN CN202211514082.2A patent/CN115798078A/en active Pending
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111881980A (en) * | 2020-07-29 | 2020-11-03 | 上海钧正网络科技有限公司 | Vehicle fault detection method and device, computer equipment and storage medium |
| CN116466689A (en) * | 2023-06-19 | 2023-07-21 | 广汽埃安新能源汽车股份有限公司 | Fault diagnosis method and device |
| CN116466689B (en) * | 2023-06-19 | 2023-09-05 | 广汽埃安新能源汽车股份有限公司 | Fault diagnosis method and device |
| CN116778717A (en) * | 2023-08-10 | 2023-09-19 | 浙江小遛信息科技有限公司 | Fault identification method and server for shared vehicle |
| CN116778717B (en) * | 2023-08-10 | 2024-01-19 | 浙江小遛信息科技有限公司 | Fault identification method and server for shared vehicle |
| CN117104377A (en) * | 2023-10-23 | 2023-11-24 | 西安小果出行科技有限公司 | Intelligent management system and method for electric bicycle |
| CN117104377B (en) * | 2023-10-23 | 2024-01-30 | 西安小果出行科技有限公司 | Intelligent management system and method for electric bicycle |
| CN117135686A (en) * | 2023-10-24 | 2023-11-28 | 深圳市蓝鲸智联科技股份有限公司 | Bluetooth-based vehicle-mounted information interaction method and system |
| CN117135686B (en) * | 2023-10-24 | 2024-02-20 | 深圳市蓝鲸智联科技股份有限公司 | Bluetooth-based vehicle-mounted information interaction method and system |
| CN117172756A (en) * | 2023-11-01 | 2023-12-05 | 深圳市信润富联数字科技有限公司 | Mold management method, apparatus, device and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115798078A (en) | Vehicle accurate fault diagnosis method and device | |
| CN110501169A (en) | Diagnostic method, device and the electronic equipment of vehicle trouble | |
| CN110910531B (en) | Rapid pavement friction coefficient detection method based on vehicle-mounted OBD information | |
| CN114585983A (en) | Method, device and system for detecting abnormal operation state of equipment | |
| CN114906011B (en) | Electric automobile mileage pre-estimation system based on intelligent navigation | |
| CN110349427A (en) | A kind of wisdom traffic management system based on big data | |
| CN110329275A (en) | In case of a fault running gear, especially vehicle device method and apparatus | |
| CN113222187B (en) | Intelligent monitoring method for brake health of shared power-assisted vehicle | |
| CN111929588B (en) | Charging safety monitoring method, device and system based on extreme learning machine | |
| CN112685466A (en) | Vehicle overload prediction model training method, overload prediction method, system and medium | |
| CN116653962A (en) | Intelligent driving vehicle efficient energy-saving system and energy-saving method | |
| CN111775711B (en) | Pure electric vehicle state monitoring method and system | |
| CN113516798B (en) | Meter adjustment vehicle judging method and device | |
| CN117057219A (en) | Tire damage prediction method, device, equipment, storage medium and vehicle | |
| CN112288524A (en) | Vehicle management method, electronic device, and computer-readable storage medium | |
| CN112307905A (en) | Road gradient self-learning method and system for vehicle predictive control | |
| CN108828980B (en) | Method and system for predicting over-bending centrifugal force | |
| CN115188086B (en) | ETC portal system dynamic monitoring method and system | |
| CN110765961A (en) | Vehicle braking state judgment method and device, computer equipment and storage medium | |
| CN107399209A (en) | The monitoring method and system of vehicle tire pressure, car terminals, memory | |
| CN113240910B (en) | Road detection method, system, equipment and storage medium based on cooperative vehicle | |
| JP2005162148A (en) | Vehicle information managing system | |
| CN109492710B (en) | New energy automobile fault detection auxiliary method | |
| US11970080B2 (en) | Information processing apparatus, information processing system, computer readable recording medium and information processing method | |
| US20240280368A1 (en) | Energy consumption predictions, feedback, and coaching for off-road activities |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |