Bicycle brake fault identification method and device, electronic equipment and storage medium

Abstract

This invention provides a method, device, electronic device, and storage medium for identifying single-vehicle brake faults. The method includes: acquiring driving data of a single-vehicle to be identified, including driving acceleration, historical mileage, and / or historical order count; applying the driving data to identify brake faults in the single-vehicle to be identified based on a first brake fault identification model, obtaining a fault identification result, wherein the fault identification result includes simultaneous left and right brake failure or non-simultaneous left and right brake failure; wherein the first brake fault identification model is trained based on the driving data and braking state of a sample single-vehicle. The single-vehicle brake fault identification method, device, electronic device, and storage medium provided by this invention achieve effective identification in cases of simultaneous left and right brake failures in a single-vehicle, thereby avoiding manual screening, reducing operating costs, and improving the accuracy and reliability of brake fault identification.

Description

Technical Field

[0001] This invention relates to the field of shared vehicle technology, and in particular to a method, device, electronic device, and storage medium for identifying single-vehicle brake malfunctions. Background Technology

[0002] Over time, shared bicycles may experience a decline in braking performance. If this is not identified and maintained promptly, it can pose safety risks to users, reduce user satisfaction, and increase operating costs for the company. Therefore, it is necessary to identify and address faults in the braking systems of shared bicycles.

[0003] Currently, brake malfunctions cannot be automatically reported and usually require manual screening, which is costly, inefficient, and requires significant investment. Furthermore, due to the wide and irregular usage areas of shared bicycles, it is easy to miss some issues. Summary of the Invention

[0004] This invention provides a method, device, electronic device, and storage medium for identifying single-vehicle brake faults, in order to solve the shortcomings of the existing technology where manual screening is labor-intensive, costly, inefficient, and prone to missed detections.

[0005] This invention provides a method for identifying single-vehicle brake malfunctions, comprising:

[0006] Obtain the driving data of the bicycle to be identified, including driving acceleration, historical mileage and / or historical order count;

[0007] Based on the first brake fault identification model, the driving data is used to identify the brakes of the vehicle to be identified, and the fault identification result is obtained. The fault identification result includes simultaneous faults of the left and right brakes or faults of neither the left nor right brakes.

[0008] The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle.

[0009] According to the single-vehicle brake fault identification method provided by the present invention, the step of identifying brake faults of the single vehicle to be identified based on the driving data using the first brake fault identification model includes:

[0010] Based on the first brake fault identification model, the driving acceleration, historical mileage, and historical order count, along with their respective weights, are applied to identify brake faults in the vehicle to be identified.

[0011] According to the single-vehicle brake fault identification method provided by the present invention, the weight corresponding to the driving acceleration is greater than the weights corresponding to the historical driving mileage and the number of historical orders, respectively.

[0012] According to the single-vehicle brake fault identification method provided by the present invention, the first brake fault identification model is trained based on the following steps:

[0013] Determine the initial decision tree model;

[0014] Based on the driving data and braking status of the sample vehicle, the initial decision tree model is trained using the random forest algorithm, and the trained initial decision tree model is determined as the first brake fault identification model.

[0015] According to the single-vehicle brake fault identification method provided by the present invention, the method further includes, based on a first brake fault identification model, applying the driving data to identify brake faults in the single vehicle to be identified, and obtaining a fault identification result, the following steps:

[0016] If the fault identification result is that the left and right brakes are not simultaneously faulty, obtain the number of times the vehicle to be identified brakes left and right within the current time period;

[0017] Based on the number of left and right braking actions, determine the left and right braking usage ratio of the bicycle to be identified within the current time period;

[0018] Based on the usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes, the brakes of the vehicle to be identified are fault identified to obtain fault identification results. The fault identification results include left brake fault, right brake fault, or normal brakes.

[0019] According to the single-vehicle brake fault identification method provided by the present invention, the step of identifying brake faults in the single-vehicle to be identified based on the left and right brake usage ratio and the historical left and right brake usage ratio includes:

[0020] Based on the second brake fault identification model, the left and right brake usage ratios and historical left and right brake usage ratios are used to identify brake faults in the vehicle to be identified.

[0021] The second brake fault identification model is trained based on the ratio of left and right brake usage of the sample vehicle in the current time period and the historical ratio of left and right brake usage, as well as the braking status of the sample vehicle.

[0022] According to the single-vehicle brake fault identification method provided by the present invention, the second brake fault identification model is obtained by training based on an ensemble learning algorithm.

[0023] The present invention also provides a single-vehicle brake fault identification device, comprising:

[0024] The driving data acquisition unit is used to acquire the driving data of the vehicle to be identified, including driving acceleration, historical mileage and / or historical order count;

[0025] The fault identification unit is used to identify the brakes of the vehicle to be identified based on the first brake fault identification model and the driving data, and to obtain the fault identification result, which includes simultaneous faults of the left and right brakes or faults of non-left and right brakes.

[0026] The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle.

[0027] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the single-vehicle brake fault identification method as described above.

[0028] The present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the single-vehicle brake fault identification method as described above.

[0029] The present invention also provides a computer program product, including a computer program that, when executed by a processor, implements the single-vehicle brake fault identification method as described above.

[0030] The single-vehicle brake fault identification method, device, electronic device, and storage medium provided by this invention identify faults by using a first brake fault identification model trained based on the driving data and braking status of sample single vehicles. This model can better distinguish the differences between driving data under normal and faulty braking conditions, and achieves effective identification when both left and right brakes of a single vehicle are faulty at the same time. This avoids manual screening, reduces operating costs, and improves the accuracy and reliability of brake fault identification. Attached Figure Description

[0031] To more clearly illustrate the technical solutions in this invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0032] Figure 1 This is a flowchart illustrating the single-vehicle brake fault identification method provided by the present invention;

[0033] Figure 2This is a schematic diagram of the structure of the single-vehicle brake fault identification device provided by the present invention;

[0034] Figure 3 This is a schematic diagram of the structure of the electronic device provided by the present invention. Detailed Implementation

[0035] To make the objectives, technical solutions, and advantages of this invention clearer, the technical solutions of this invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of this invention. All other embodiments obtained by those skilled in the art based on the embodiments of this invention without creative effort are within the scope of protection of this invention.

[0036] To facilitate a clear description of the technical solutions of the embodiments of the present invention, the terms "first" and "second" are used in the embodiments of the present invention to distinguish the same or similar items with essentially the same function and effect. Those skilled in the art can understand that the terms "first" and "second" are not intended to limit the quantity or execution order.

[0037] Currently, shared bicycles cannot automatically report brake malfunctions, requiring manual screening, which is costly, inefficient, and involves significant investment. Furthermore, the wide and unpredictable nature of shared bicycle usage makes it easy to miss issues.

[0038] Based on this, embodiments of the present invention provide a method for identifying single-vehicle brake faults, which enables automatic identification of single-vehicle brake faults and timely maintenance of single-vehicles with identified brake faults, thereby ensuring user safety.

[0039] Figure 1 This is a flowchart illustrating the single-vehicle brake fault identification method provided by the present invention. The executing entity for each step of this method can be a single-vehicle brake fault identification device. This device can be implemented through software and / or hardware. The single-vehicle brake fault identification device can be integrated into an electronic device, which can be a personal computer, server, cloud device, or mobile device such as a smartphone or tablet. Figure 1 As shown, the single-vehicle brake fault identification method provided in this embodiment of the invention includes the following steps:

[0040] Step 110: Obtain the driving data of the bicycle to be identified. The driving data includes driving acceleration, historical mileage and / or historical order count.

[0041] Specifically, the bicycle to be identified is the bicycle for which brake malfunction identification needs to be performed. Here, the bicycle is a shared bicycle equipped with a smart central control system. Specifically, it can be a shared bicycle or a shared electric bicycle. This embodiment of the invention does not make specific limitations on this.

[0042] Optionally, a six-axis accelerometer can be pre-installed on the bicycle. This sensor can collect the bicycle's acceleration in real time, continuously collecting acceleration data from the start of the trip. Alternatively, acceleration data can be collected only after a braking signal is received. The choice can be made flexibly based on actual usage. The lower the braking acceleration, the greater the risk of decreased braking performance; conversely, the greater the braking acceleration, the lower the risk of decreased braking performance.

[0043] Each time a user finishes using a bike, an order record is generated, which can then be used to calculate the mileage of the bike under that order. The historical mileage can be the total mileage since the bike was put into operation, and the historical mileage can also be statistically analyzed in stages according to time periods, such as monthly, quarterly or annually.

[0044] Historical order count refers to the number of orders placed by users using a bicycle since it was put into operation. Of course, historical order count can also be recorded by month, quarter or year according to the order generation time.

[0045] Understandably, historical mileage and historical order count can reflect the frequency of a vehicle's use. The higher the frequency of a vehicle's use, the greater the risk of a decline in braking system performance; conversely, the lower the frequency of a vehicle's use, the lower the risk of a decline in braking system performance.

[0046] Step 120: Based on the first brake fault identification model, apply driving data to identify the brakes of the vehicle to be identified and obtain the fault identification result. The fault identification result includes simultaneous faults of the left and right brakes or simultaneous faults of the left and right brakes.

[0047] The first brake fault identification model is trained based on the driving data and braking status of the sample vehicles.

[0048] Specifically, after obtaining the driving data of the bicycle to be identified in step 110, the driving data can be used to identify brake faults in the bicycle based on the first brake fault identification model. Specifically, the driving data of the bicycle to be identified can be input into the first brake fault identification model to obtain the fault identification results output by the first brake fault identification model. The fault identification results include simultaneous faults in both left and right brakes or faults in other brakes.

[0049] Typically, bicycles have brakes on both the left and right sides, and these brakes are independent of each other. This means that if one brake is damaged, it will not affect the use of the other. Brake damage can usually include at least one of the following: a damaged brake lever, damaged brake pads, or damaged brake cables.

[0050] Simultaneous failure of both left and right brakes indicates that neither of the left nor right brakes on the bicycle can be used normally, and the bicycle's braking system is completely damaged. Simultaneous failure of both left and right brakes indicates that the left and right brakes on the bicycle do not fail at the same time. This may include three situations: 1) The left brake of the bicycle is faulty, while the right brake is normal; 2) The left brake of the bicycle is normal, while the right brake is faulty; 3) The left brake of the bicycle is normal, while the right brake is normal.

[0051] Before performing step 120, the first brake fault identification model can be trained in advance. Specifically, the model can be trained using the following method:

[0052] The braking states of the sample bicycles can include simultaneous failure of both left and right brakes or failure of only one brake. For the sample bicycles in these two braking states, a large amount of driving data can be collected first. Then, the driving data of the sample bicycles is input into an initial model for training. During the training process, the initial model can learn the differences in the driving data between the two braking states. The first brake fault recognition model trained in this way can better distinguish the differences between driving data under normal braking and fault conditions.

[0053] The method provided in this invention identifies faults by training a first brake fault identification model based on the driving data and braking status of a sample vehicle. This method can better distinguish the differences between driving data under normal and faulty braking conditions, and achieves effective identification when both left and right brakes of a vehicle are faulty at the same time. This avoids manual screening, reduces operating costs, and improves the accuracy and reliability of brake fault identification.

[0054] Based on the above embodiments, step 120, based on the first brake fault identification model, applies driving data to identify brake faults in the vehicle to be identified, including:

[0055] Based on the first brake fault identification model, driving acceleration, historical mileage, and historical order count, along with their respective weights, are applied to identify brake faults in the vehicle to be identified.

[0056] Specifically, when identifying brake faults in a single vehicle, the weights corresponding to driving acceleration, historical mileage, and historical order count can be considered simultaneously. These weights reflect the importance of driving acceleration, historical mileage, and historical order count in brake fault identification, and can also be expressed as correlation coefficients between each driving data point and brake fault identification.

[0057] Understandably, the greater the correlation with brake malfunction identification, the greater its corresponding weight; conversely, the less the correlation, the less its corresponding weight. It should be noted that "greater" and "less" here are relative, comparing three driving data points: driving acceleration, historical mileage, and historical order count.

[0058] The weights corresponding to driving acceleration, historical mileage, and historical order count can be preset or determined by the first brake fault identification model during training. This embodiment of the invention does not impose specific limitations on these weights.

[0059] Based on any of the above embodiments, the weight corresponding to driving acceleration is greater than the weights corresponding to historical driving mileage and historical order count, respectively.

[0060] Specifically, in the case of simultaneous failure of both left and right brakes, where the braking system of a single vehicle completely fails, the closer the braking acceleration is to zero during driving, the greater the weight of driving acceleration can be compared to the weights of historical mileage and historical order count. In other words, when the braking system of a single vehicle completely fails, driving acceleration is more important for brake fault identification than historical mileage and historical order count.

[0061] Based on any of the above embodiments, the first brake fault identification model is trained using the following steps:

[0062] Determine the initial decision tree model;

[0063] Based on the driving data and braking status of the sample bicycles, the random forest algorithm is applied to train the initial decision tree model.

[0064] The first brake fault identification model is determined based on the trained initial decision tree model.

[0065] Specifically, the first brake fault identification model can be trained through the following steps:

[0066] First, an initial decision tree model is determined, typically at least two. Features can be randomly selected from the driving data of sample vehicles, such as acceleration, historical mileage, or historical order count. Then, the randomly selected acceleration and historical mileage features are input into the initial decision tree model for training, resulting in a complete decision tree model, known as a random forest. Finally, the first brake fault identification model is determined based on the trained initial decision tree model.

[0067] The method provided in this embodiment of the invention, for cases where the driving data of a sample vehicle includes acceleration, historical mileage and historical order count, uses a random forest algorithm to train a first brake fault identification model. The first brake fault identification model trained in this way provides accuracy and reliability for fault identification.

[0068] Based on any of the above embodiments, step 120 involves using the driving data to identify the brakes of the vehicle to be identified based on the first brake fault identification model to obtain a fault identification result, followed by:

[0069] If the fault identification result indicates that the left and right brakes are not simultaneously faulty, obtain the number of left and right brakes of the vehicle to be identified within the current time period.

[0070] Based on the number of left and right braking operations, determine the proportion of left and right braking usage of the bicycle to be identified in the current time period;

[0071] Based on the usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes, the brakes of the bicycle to be identified are fault identified, and the fault identification results are obtained. The fault identification results include left brake fault, right brake fault, or normal brake.

[0072] Specifically, as described in the above embodiments, the method provided by the present invention can identify a single vehicle with both left and right brakes malfunctioning simultaneously. In order to further improve the accuracy of fault identification, when the fault identification result is not that both left and right brakes are malfunctioning simultaneously, it can further identify whether one of the left and right brakes is malfunctioning.

[0073] It should be noted that this method is for scenarios where the bicycle central control device can distinguish between the left and right brake levers. When the bicycle central control device receives a brake signal, it can distinguish which brake lever the brake signal comes from.

[0074] First, the bicycle's central control device acquires the number of times the bicycle to be identified brakes left and right within the current time period. The current time period can be a preset fault identification cycle, such as weekly or monthly, and this embodiment of the invention does not specifically limit this. When the user operates the brake lever once during riding, the central control device will distinguish whether the brake signal comes from the left or right brake lever, and then count the number of times the bicycle brakes left and right.

[0075] After obtaining the number of times the bicycle braked left and right, the usage ratio of left and right brakes in the current time period can be determined, for example, left brake usage ratio of 60% and right brake usage ratio of 40%. Furthermore, the historical usage ratio of left and right brakes for this bicycle can be calculated.

[0076] Then, the usage ratio of the left and right brakes of the bicycle in the current time period is compared with the historical usage ratio of the left and right brakes. Fault identification is then performed on the brakes of the bicycle to be identified, and the fault identification results are obtained. The fault identification results include left brake fault, right brake fault, or normal brake. Here, left brake fault means left brake is faulty and right brake is normal; right brake fault means right brake is faulty and left brake is normal; normal brake means both left and right brakes are normal.

[0077] Understandably, if the usage ratio of the left and right brakes is relatively close in the current time period, and the historical usage ratio of the left and right brakes is also relatively close, it can be assumed that both brakes are normal. If the usage ratio of the left and right brakes in the current time period differs significantly from the historical usage ratio, then one of the brakes may be malfunctioning.

[0078] The method provided in this invention can effectively identify a bicycle with a brake malfunction on one side by using the left and right brake usage ratio and the historical left and right brake usage ratio.

[0079] Based on any of the above embodiments, based on the usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes, fault identification is performed on the brakes of the bicycle to be identified, including:

[0080] Based on the second brake fault identification model, the usage ratio of left and right brakes and the historical usage ratio of left and right brakes are used to identify brake faults in the single vehicle to be identified.

[0081] The second brake fault identification model is trained based on the ratio of left and right brake usage of the sample vehicle in the current time period and the historical ratio of left and right brake usage, as well as the braking status of the sample vehicle.

[0082] Specifically, the left and right brake faults can be further identified based on the second brake fault identification model. The usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes can be input into the trained second brake fault identification model to obtain the identification results output by the second brake fault identification model. The identification results include left brake fault, right brake fault, or normal brakes.

[0083] Prior to this, the second brake fault identification model can be trained in advance. Specifically, the model can be trained using the following methods:

[0084] The braking status of the sample bicycles can include left brake failure, right brake failure, or normal braking. For the sample bicycles in these three braking statuses, we can first collect the usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes of a large number of sample bicycles.

[0085] Subsequently, the usage ratio of the left and right brakes of the sample bicycles, as well as the historical usage ratio of the left and right brakes, were input into the initial model for training. The first brake fault recognition model trained in this way can better distinguish the differences between the usage ratios of the left and right brakes when the left brake is faulty, the right brake is faulty, or the brakes are in normal condition.

[0086] Furthermore, ensemble learning algorithms can be used for training. Considering that the second brake fault identification model uses fewer features than the first brake fault identification model, parallel or serial ensemble learning algorithms can be selected.

[0087] Based on any of the above embodiments, a method for identifying single-vehicle brake faults is provided, including:

[0088] S1. For bicycles that cannot distinguish between left and right brake lever signals, obtain the driving data of the bicycle to be identified. The driving data includes driving acceleration, historical mileage and / or historical order count.

[0089] S2, based on the first brake fault identification model, the driving data is used to identify the brakes of the vehicle to be identified, and the fault identification result is obtained. The fault identification result includes simultaneous faults of the left and right brakes or simultaneous faults of the left and right brakes. The first brake fault identification model is trained by the random forest algorithm based on the driving data of the sample vehicle and the braking state of the sample vehicle.

[0090] S3. For bicycles that can distinguish between left and right brake lever signals, if the fault identification result is that the left and right brakes are not simultaneously faulty, obtain the number of left and right brakes of the bicycle to be identified in the current time period; based on the number of left and right brakes, determine the left and right brake usage ratio of the bicycle to be identified in the current time period.

[0091] S4. Based on the usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes, the brakes of the vehicle to be identified are fault identified through an integrated learning algorithm to obtain fault identification results. The fault identification results include left brake fault, right brake fault, or normal brakes.

[0092] The single-vehicle brake fault identification device provided by the present invention is described below. The single-vehicle brake fault identification device described below and the single-vehicle brake fault identification method described above can be referred to in correspondence.

[0093] Figure 2 This is a structural schematic diagram of the single-vehicle brake fault identification device provided by the present invention, as shown below. Figure 2 As shown, the single-vehicle brake fault identification device includes a driving data acquisition unit 210 and a fault identification unit 220, wherein:

[0094] The driving data acquisition unit 210 is used to acquire driving data of the vehicle to be identified, including driving acceleration, historical mileage and / or historical order count;

[0095] The fault identification unit 220 is used to identify the brakes of the vehicle to be identified based on the first brake fault identification model and the driving data, and to obtain the fault identification result. The fault identification result includes simultaneous faults of the left and right brakes or simultaneous faults of the left and right brakes.

[0096] The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle.

[0097] The single-vehicle brake fault identification device provided in this embodiment of the invention identifies faults by training a first brake fault identification model based on the driving data and braking status of a sample single vehicle. This model can better distinguish the differences between driving data under normal and faulty braking conditions, and achieves effective identification when both left and right brakes of a single vehicle are faulty at the same time. This avoids manual screening, reduces operating costs, and improves the accuracy and reliability of brake fault identification.

[0098] Based on any of the above embodiments, the fault identification unit 220 is further configured to:

[0099] Based on the first brake fault identification model, the driving acceleration, historical mileage, and historical order count, along with their respective weights, are applied to identify brake faults in the vehicle to be identified.

[0100] Based on any of the above embodiments, the weight corresponding to the driving acceleration is greater than the weights corresponding to the historical driving mileage and the number of historical orders, respectively.

[0101] Based on any of the above embodiments, the single-vehicle brake fault identification device further includes a model training unit, used for:

[0102] Determine the initial decision tree model;

[0103] Based on the driving data and braking status of the sample vehicle, the initial decision tree model is trained using the random forest algorithm, and the trained initial decision tree model is determined as the first brake fault identification model.

[0104] Based on any of the above embodiments, the single-vehicle brake fault identification device further includes left and right brake fault identification units, used for:

[0105] If the fault identification result is that the left and right brakes are not simultaneously faulty, obtain the number of times the vehicle to be identified brakes left and right within the current time period;

[0106] Based on the number of left and right braking actions, determine the left and right braking usage ratio of the bicycle to be identified within the current time period;

[0107] Based on the usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes, the brakes of the vehicle to be identified are fault identified to obtain fault identification results. The fault identification results include left brake fault, right brake fault, or normal brakes.

[0108] Based on any of the above embodiments, the left and right brake fault identification units are further configured to:

[0109] Based on the second brake fault identification model, the left and right brake usage ratios are used to identify brake faults in the vehicle to be identified.

[0110] The second brake fault identification model is trained based on the ratio of left and right brake usage of the sample vehicle in the current time period and the historical ratio of left and right brake usage, as well as the braking status of the sample vehicle.

[0111] Based on any of the above embodiments, the second brake fault identification model is obtained by training an ensemble learning algorithm.

[0112] Figure 3 An example is a schematic diagram of the physical structure of an electronic device, such as... Figure 3 As shown, the electronic device may include a processor 310, a communication interface 320, a memory 330, and a communication bus 340, wherein the processor 310, the communication interface 320, and the memory 330 communicate with each other via the communication bus 340. The processor 310 can call logical instructions in the memory 330 to execute a single-vehicle brake fault identification method, which includes: acquiring the driving data of the single vehicle to be identified, the driving data including driving acceleration, and historical mileage and / or historical order count;

[0113] Based on the first brake fault identification model, the driving data is used to identify the brakes of the vehicle to be identified, and the fault identification result is obtained. The fault identification result includes simultaneous faults of the left and right brakes or faults of neither the left nor right brakes.

[0114] The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle.

[0115] Furthermore, the logical instructions in the aforementioned memory 330 can be implemented as software functional units and, when sold or used as independent products, can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0116] On the other hand, the present invention also provides a computer program product, the computer program product comprising a computer program that can be stored on a non-transitory computer-readable storage medium, wherein when the computer program is executed by a processor, the computer is able to execute the single-vehicle brake fault identification method provided by the above methods, the method comprising:

[0117] Obtain the driving data of the bicycle to be identified, including driving acceleration, historical mileage and / or historical order count;

[0118] Based on the first brake fault identification model, the driving data is used to identify the brakes of the vehicle to be identified, and the fault identification result is obtained. The fault identification result includes simultaneous faults of the left and right brakes or faults of neither the left nor right brakes.

[0119] The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle.

[0120] In another aspect, the present invention also provides a non-transitory computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, is implemented to perform the single-vehicle brake fault identification method provided by the above methods, the method comprising:

[0121] Obtain the driving data of the bicycle to be identified, including driving acceleration, historical mileage and / or historical order count;

[0122] Based on the first brake fault identification model, the driving data is used to identify the brakes of the vehicle to be identified, and the fault identification result is obtained. The fault identification result includes simultaneous faults of the left and right brakes or faults of neither the left nor right brakes.

[0123] The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle.

[0124] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0125] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0126] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for identifying a bicycle brake failure, characterized by, include: Obtain the driving data of the bicycle to be identified, including driving acceleration, historical mileage and / or historical order count; Based on the first brake fault identification model, the driving data is used to identify the brakes of the vehicle to be identified, and the fault identification result is obtained. The fault identification result includes simultaneous faults of the left and right brakes or faults of neither the left nor right brakes. The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle. The first brake fault identification model was trained based on the following steps: An initial decision tree model is determined; based on the driving data and braking status of the sample vehicle, the random forest algorithm is applied to train the initial decision tree model; a first brake fault identification model is determined based on the trained initial decision tree model. If the fault identification result is that the left and right brakes are not simultaneously faulty, the number of times the bicycle to be identified brakes left and right within the current time period is obtained; based on the number of times the left and right brakes are braked left and right within the current time period, the usage ratio of the left and right brakes of the bicycle to be identified is determined; based on the usage ratio of the left and right brakes and the historical usage ratio of the left and right brakes, the brakes of the bicycle to be identified are faulty, and the fault identification result is obtained, which includes left brake fault, right brake fault, or brakes normal. The method of identifying brake malfunctions in the bicycle to be identified based on the left and right brake usage ratio and historical left and right brake usage ratios includes: Based on the second brake fault identification model, the left and right brake usage ratios are used to identify brake faults in the vehicle to be identified. The second brake fault identification model is trained based on the ratio of left and right brake usage of the sample vehicle in the current time period and the historical ratio of left and right brake usage, as well as the braking status of the sample vehicle; the second brake fault identification model is trained based on an ensemble learning algorithm.

2. The single-vehicle brake fault identification method according to claim 1, characterized in that, The step of using the driving data to identify brake faults in the vehicle to be identified, based on the first brake fault identification model, includes: Based on the first brake fault identification model, the driving acceleration, historical mileage, and historical order count, as well as the weights corresponding to the driving acceleration, historical mileage, and historical order count, are applied to identify brake faults in the vehicle to be identified.

3. The single-vehicle brake fault identification method according to claim 2, characterized in that, The weight corresponding to the driving acceleration is greater than the weights corresponding to the historical driving mileage and the number of historical orders, respectively.

4. A single-vehicle brake fault identification device, characterized in that, include: The driving data acquisition unit is used to acquire the driving data of the vehicle to be identified, including driving acceleration, historical mileage and / or historical order count; The fault identification unit is used to identify the brakes of the vehicle to be identified based on the first brake fault identification model and the driving data, and to obtain the fault identification result. The fault identification result includes simultaneous faults of the left and right brakes or simultaneous faults of the left and right brakes. The first brake fault identification model is trained based on the driving data of the sample vehicle and the braking status of the sample vehicle. The first brake fault identification model was trained based on the following steps: An initial decision tree model is determined; based on the driving data and braking status of the sample vehicle, the random forest algorithm is applied to train the initial decision tree model; a first brake fault identification model is determined based on the trained initial decision tree model. The left and right brake fault identification unit is used to obtain the number of left and right brakes of the bicycle to be identified in the current time period when the fault identification result is that the left and right brakes are not simultaneously faulty; based on the number of left and right brakes, determine the left and right brake usage ratio of the bicycle to be identified in the current time period; based on the left and right brake usage ratio and the historical left and right brake usage ratio, perform fault identification on the brakes of the bicycle to be identified to obtain a fault identification result, which includes left brake fault, right brake fault, or brake normal; The method of identifying brake malfunctions in the bicycle to be identified based on the left and right brake usage ratio and historical left and right brake usage ratios includes: Based on the second brake fault identification model, the left and right brake usage ratios are used to identify brake faults in the vehicle to be identified. The second brake fault identification model is trained based on the ratio of left and right brake usage of the sample vehicle in the current time period and the historical ratio of left and right brake usage, as well as the braking status of the sample vehicle; the second brake fault identification model is trained based on an ensemble learning algorithm.

5. An electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the single-vehicle brake fault identification method as described in any one of claims 1 to 3.

6. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the single-vehicle brake fault identification method as described in any one of claims 1 to 3.

Images