Regeneration failure prediction method and device, computer device and storage medium

Abstract

The application relates to a regenerative fault prediction method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: acquiring diagnosis basis data in a preset time period, the diagnosis basis data being extracted based on vehicle operation data reported by a vehicle in the preset time period; determining a plurality of preset fault modes corresponding to respective flag bits based on the diagnosis basis data, the flag bits being used for indicating whether an anomaly exists in the vehicle under the corresponding fault mode; determining a vehicle corresponding anomaly code according to the plurality of preset fault modes corresponding to the respective flag bits, and performing validity analysis on each flag bit in the vehicle corresponding anomaly code; updating the anomaly code based on the validity analysis result to obtain an updated anomaly code; and determining a regenerative fault prediction result based on the updated anomaly code. The method can prevent problems such as vehicle downtime caused by frequent regenerative faults.

Description

Technical Field

[0001] This application relates to the field of vehicle technology, and in particular to a method, apparatus, computer equipment, storage medium, and computer program product for predicting regenerative faults. Background Technology

[0002] With the development of vehicle technology, the types and functions of vehicles are becoming increasingly diverse. Vehicles are equipped with particulate filters to collect soot. As more and more black smoke is collected in the particulate filter, it gradually leads to high exhaust back pressure, which affects engine power. The process of burning off this collected black smoke by heating the exhaust is called regeneration. Predicting regeneration failures is still in the technological gap stage and is an urgent problem to be solved in this field. Summary of the Invention

[0003] Therefore, it is necessary to provide a method, apparatus, computer equipment, computer-readable storage medium, and computer program product for predicting regenerative faults in response to the above-mentioned technical problems.

[0004] Firstly, this application provides a method for predicting regenerative failures. The method includes:

[0005] Obtain diagnostic data within a preset time period. The diagnostic data is extracted from the vehicle operation data reported by the vehicle within the preset time period.

[0006] Based on diagnostic data, flag bits corresponding to each of the preset fault modes are determined. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0007] Based on the flag bits corresponding to each of the multiple preset fault modes, the corresponding abnormal code of the vehicle is determined, and the validity analysis of each flag bit in the corresponding abnormal code of the vehicle is performed. Based on the results of the validity analysis, the abnormal code is updated to obtain the updated abnormal code.

[0008] Based on the updated anomaly code, the regenerative fault prediction result is determined.

[0009] Secondly, this application also provides a regenerative fault prediction device. The device includes:

[0010] The acquisition module is used to acquire diagnostic basis data within a preset time period. The diagnostic basis data is extracted based on the vehicle operation data reported by the vehicle within the preset time period.

[0011] The determination module is used to determine the flag bits corresponding to each of the preset multiple fault modes based on diagnostic data. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0012] The determination module is also used to determine the abnormal code corresponding to the vehicle based on the flag bits corresponding to each of the multiple preset fault modes, and to perform validity analysis on each flag bit in the abnormal code corresponding to the vehicle, and update the abnormal code based on the validity analysis results to obtain the updated abnormal code.

[0013] The determination module is also used to determine the cause of vehicle regeneration failure based on the updated exception code.

[0014] Thirdly, this application also provides a computer device. The computer device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to perform the following steps:

[0015] Obtain diagnostic data within a preset time period. The diagnostic data is extracted from the vehicle operation data reported by the vehicle within the preset time period.

[0016] Based on diagnostic data, flag bits corresponding to each of the preset fault modes are determined. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0017] Based on the flag bits corresponding to each of the multiple preset fault modes, the corresponding abnormal code of the vehicle is determined, and the validity analysis of each flag bit in the corresponding abnormal code of the vehicle is performed. Based on the results of the validity analysis, the abnormal code is updated to obtain the updated abnormal code.

[0018] Based on the updated anomaly code, the regenerative fault prediction result is determined.

[0019] Fourthly, this application also provides a computer-readable storage medium. The computer-readable storage medium stores a computer program thereon, which, when executed by a processor, performs the following steps:

[0020] Obtain diagnostic data within a preset time period. The diagnostic data is extracted from the vehicle operation data reported by the vehicle within the preset time period.

[0021] Based on diagnostic data, flag bits corresponding to each of the preset fault modes are determined. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0022] Based on the flag bits corresponding to each of the multiple preset fault modes, the corresponding abnormal code of the vehicle is determined, and the validity analysis of each flag bit in the corresponding abnormal code of the vehicle is performed. Based on the results of the validity analysis, the abnormal code is updated to obtain the updated abnormal code.

[0023] Based on the updated anomaly code, the regenerative fault prediction result is determined.

[0024] Fifthly, this application also provides a computer program product. The computer program product includes a computer program that, when executed by a processor, performs the following steps:

[0025] Obtain diagnostic data within a preset time period. The diagnostic data is extracted from the vehicle operation data reported by the vehicle within the preset time period.

[0026] Based on diagnostic data, flag bits corresponding to each of the preset fault modes are determined. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0027] Based on the flag bits corresponding to each of the multiple preset fault modes, the corresponding abnormal code of the vehicle is determined, and the validity analysis of each flag bit in the corresponding abnormal code of the vehicle is performed. Based on the results of the validity analysis, the abnormal code is updated to obtain the updated abnormal code.

[0028] Based on the updated anomaly code, the regenerative fault prediction result is determined.

[0029] The aforementioned regeneration fault prediction method, device, computer equipment, storage medium, and computer program product can acquire diagnostic data of the vehicle within a preset time period. This diagnostic data is extracted from vehicle operation data reported by the vehicle within the preset time period. Based on the diagnostic data, flag bits corresponding to multiple preset fault modes are determined. These flag bits indicate whether the vehicle exhibits an abnormality under the corresponding fault mode. Based on the flag bits corresponding to the multiple preset fault modes, the corresponding abnormal code for the vehicle is determined, and the validity of each flag bit in the abnormal code is analyzed. The abnormal code is updated based on the validity analysis results to obtain an updated abnormal code. Based on the updated abnormal code, the regeneration fault prediction result is determined. This fault prediction result can be used to assess the vehicle's regeneration function. When an abnormality in the regeneration function is detected, the vehicle owner can be contacted promptly for repairs, preventing frequent regeneration faults that could lead to vehicle downtime. Attached Figure Description

[0030] Figure 1 This is a diagram illustrating the application environment of a regenerative fault prediction method in one embodiment.

[0031] Figure 2 This is a flowchart illustrating a regenerative fault prediction method in one embodiment;

[0032] Figure 3 This is a flowchart illustrating the regenerative fault prediction method in another embodiment;

[0033] Figure 4 This is a flowchart illustrating the regenerative fault prediction method in yet another embodiment;

[0034] Figure 5 This is a structural block diagram of a regenerative fault prediction device in one embodiment;

[0035] Figure 6 This is an internal structural diagram of a computer device in one embodiment. Detailed Implementation

[0036] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0037] The regenerative fault prediction method provided in this application can be applied to, for example, Figure 1 In the application environment shown, vehicle 102 communicates with server 104 via a network. A data storage system can store the data that server 104 needs to process. The data storage system can be integrated onto server 104 or placed on the cloud or other network servers. Vehicle 102 can report collected data to server 104 at a preset frequency. Server 104 can extract information from the collected data reported by vehicle 102 to obtain key extracted information. Server 104 can use the key extracted information as diagnostic basis data. Based on the diagnostic basis data, it determines the flag bits corresponding to each of several preset fault modes. Based on the flag bits corresponding to each of the several preset fault modes, it determines the corresponding abnormal code for the vehicle and performs validity analysis on each flag bit in the abnormal code. Based on the validity analysis results, it updates the abnormal code to obtain an updated abnormal code. Based on the updated abnormal code, it determines the recurrence fault prediction result.

[0038] Among them, vehicle 102 can be a commercial vehicle or a passenger vehicle, and server 104 can be implemented by an independent server or a server cluster composed of multiple servers.

[0039] In one embodiment, such as Figure 2 As shown, a regenerative fault prediction method is provided, which is applied to... Figure 1 Taking the server in the example, the following steps are included:

[0040] Step 202: Obtain diagnostic basis data within a preset time period. The diagnostic basis data is extracted from the vehicle operation data reported by the vehicle within the preset time period.

[0041] The regeneration fault prediction method provided in this application embodiment can be executed periodically, for example, once every Sunday. The preset time period can be the time interval between the current execution and the previous execution. For example, if the regeneration fault prediction method provided in this application embodiment is executed every Sunday, the preset time period for executing the regeneration fault prediction method provided in this application embodiment on a given Sunday is from the early morning of the previous Sunday to the early morning of this Sunday. The server can use the regeneration fault prediction method provided in this application embodiment to determine the cause of regeneration faults for each vehicle connected to the server network.

[0042] The vehicle is equipped with a Diesel Particulate Filter (DPF) differential pressure sensor, a DPF exhaust volume flow rate sensor, an upstream nitrogen oxide sensor for the Selective Catalytic Reduction (SCR) unit, a downstream nitrogen oxide sensor for the SCR unit, an inlet temperature sensor for the SCR unit, an outlet temperature sensor for the SCR unit, and a vehicle speed sensor.

[0043] The vehicle is also equipped with a remote communication terminal (Tbox). After the vehicle starts, the DPF differential pressure sensor collects the DPF differential pressure at a preset frequency, the DPF exhaust volume flow rate sensor collects the DPF exhaust volume flow rate at a preset frequency, the upstream nitrogen oxide sensor of the SCR unit collects the nitrogen oxide content in the exhaust gas input to the SCR unit at a preset frequency, the downstream nitrogen oxide sensor of the SCR unit collects the nitrogen oxide content in the exhaust gas output from the SCR unit at a preset frequency, and the inlet temperature sensor of the SCR unit collects the inlet temperature of the SCR unit at a preset frequency. All of these sensors can send the collected data to the remote communication terminal (Tbox). The remote communication terminal (Tbox) then reports the collected data to the server at a preset frequency.

[0044] Optionally, the preset frequency can be flexibly determined according to the actual situation. For example, the preset frequency can be 1Hz, but this application embodiment does not limit it.

[0045] Specifically, for each vehicle connected to the server network, the server can process the data reported by that vehicle within the previous day at a preset time each day. In particular, the server can extract information from the collected data to obtain the key extracted information of that vehicle for that day, and the server can store the key extracted information of all vehicles for that day.

[0046] For example, the preset time can be early morning every day, and the server can process the collected data reported by vehicles in the past day at early morning every day.

[0047] As described above, the regenerative fault prediction method provided in this application embodiment can be executed periodically. The preset time period can be the time interval between the current execution and the previous execution. For each vehicle connected to the server network, the server can extract key extraction information corresponding to the vehicle within the preset time period from the database, and use the extracted key extraction information as diagnostic basis data within the preset time period.

[0048] For example, the regeneration fault prediction method provided in this application is executed once every Sunday. For a certain Sunday, the preset time period is from the early morning of the previous Sunday to the early morning of this Sunday. For each vehicle connected to the server network, the server can extract the key extraction information corresponding to the vehicle from the database during the period from the early morning of the previous Sunday to the early morning of this Sunday. The extracted key extraction information is used as the diagnostic basis data within the preset time period. Then, the following steps are used to determine the cause of the regeneration fault of the vehicle.

[0049] Step 204: Based on the diagnostic data, determine the flag bits corresponding to each of the preset multiple fault modes. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0050] The preset multiple fault modes may include at least one of the following: frequent regeneration fault mode, insufficient regeneration fault mode, sulfur poisoning fault mode, abnormal water ingress fault mode, abnormal wiring harness fault mode, high carbon soot fault mode, and multiple ash fault modes.

[0051] The server can extract key information within a preset time period from the database, use the extracted key information as diagnostic basis data within the preset time period, and determine the flag bits corresponding to each of the preset multiple fault modes based on the diagnostic basis data.

[0052] The flag value is set to the first preset value, indicating that the vehicle has an abnormality in the corresponding fault mode. The flag value is set to the second preset value, indicating that the vehicle does not have an abnormality in the corresponding fault mode. The first and second preset values ​​can be flexibly set according to the situation. For example, the first preset value can be 1 and the second preset value can be 0.

[0053] Step 206: Determine the abnormal code corresponding to the vehicle based on the flag bits corresponding to each of the preset multiple fault modes, perform validity analysis on each flag bit in the abnormal code corresponding to the vehicle, update the abnormal code based on the validity analysis results, and obtain the updated abnormal code.

[0054] Once the server obtains the flag bits corresponding to each of the multiple preset fault modes, it can arrange the flag bits corresponding to each of the multiple preset fault modes in a certain order to obtain the corresponding fault code of the vehicle.

[0055] After obtaining the abnormal code corresponding to the vehicle, the server can combine the mutual influence between multiple preset fault modes to perform validity analysis on each flag bit in the abnormal code corresponding to the vehicle, thereby determining which flag bits corresponding to fault modes in the abnormal code are valid and which flag bits corresponding to fault modes are invalid. Based on the validity analysis results, the flag bits in the abnormal code are updated to obtain the updated abnormal code.

[0056] Step 208: Determine the regeneration fault prediction result based on the updated anomaly code.

[0057] After receiving the update exception code, the server extracts the flag bits with the first preset value from the update exception code and obtains the fault modes corresponding to these flag bits. Based on these fault modes, the server determines the regeneration fault prediction result of the vehicle. The regeneration fault prediction result includes the regeneration fault type and the regeneration fault cause.

[0058] After obtaining the vehicle's regeneration fault prediction result, the server can search for matching repair suggestion documents based on the prediction result and send the regeneration fault prediction result and the found repair suggestion documents to the service station. The repair personnel at the server station will then contact the vehicle owner to advance the repair of the vehicle's regeneration function.

[0059] The server obtains the update anomaly codes corresponding to all vehicles connected to the server network, aggregates and analyzes all update anomaly codes, generates a Business Intelligence (BI) report, and sends the BI report to quality control personnel so that they can identify the quality risks of a large-scale outbreak of recurring anomalies in advance and monitor the overall quality improvement.

[0060] For example, the update exception code is 1011100, where 1 indicates the existence of an exception and 0 indicates the absence of an exception. The first flag bit is the flag bit corresponding to the frequent regeneration fault mode, the second flag bit is the flag bit corresponding to the insufficient regeneration fault mode, the third flag bit is the flag bit corresponding to the sulfur poisoning fault mode, the fourth flag bit is the flag bit corresponding to the water ingress fault mode, the fifth flag bit is the flag bit corresponding to the wiring harness fault mode, the sixth flag bit is the flag bit corresponding to the high carbon soot fault mode, and the seventh flag bit is the flag bit corresponding to the high ash content fault mode. From this update exception code, it can be determined that the vehicle has frequent regeneration fault, sulfur poisoning fault, DPF water ingress fault, and DPF wiring harness fault. It can be determined that the vehicle's regeneration fault type is frequent regeneration fault, and the regeneration fault cause is sulfur poisoning, DPF water ingress, and DPF wiring harness fault.

[0061] In the above embodiments, during the regeneration fault prediction process, for each vehicle connected to the server network, diagnostic data for that vehicle within a preset time period can be obtained. This diagnostic data is extracted from vehicle operation data reported by the vehicle within the preset time period. Based on the diagnostic data, flag bits corresponding to multiple preset fault modes are determined. These flag bits indicate whether the vehicle exhibits an anomaly under the corresponding fault mode. Based on the flag bits corresponding to the multiple preset fault modes, the corresponding anomaly code for the vehicle is determined, and the validity of each flag bit in the anomaly code is analyzed. The anomaly code is updated based on the validity analysis results to obtain an updated anomaly code. Based on the updated anomaly code, the regeneration fault prediction result is determined. This fault prediction result can be used to assess the performance of the vehicle's regeneration function. When an anomaly is detected in the regeneration function, the vehicle owner is contacted promptly for repairs, preventing frequent regeneration faults that could lead to vehicle downtime.

[0062] In some embodiments, before obtaining diagnostic basis data within a preset time period, the method further includes: at each preset moment within the preset time period, determining the vehicle operation data to be processed at the current preset moment, extracting information from the vehicle operation data to be processed at the current preset moment to obtain key extraction information corresponding to the current preset moment, and storing the key extraction information; obtaining diagnostic basis data within the preset time period includes: using the stored key extraction information corresponding to each preset moment as diagnostic basis data within the preset time period.

[0063] For each vehicle connected to the server network, the method provided in this application embodiment can be used to obtain diagnostic data within a preset time period. As described above, the regenerative fault prediction method provided in this application embodiment can be executed periodically, for example, once every Sunday. The preset time period can be the time interval between the current execution and the last execution.

[0064] The preset time can be a pre-defined time for executing the information extraction steps; for example, the preset time could be the early morning of each day. For each preset time within a preset time period, the vehicle operation data to be processed at the current preset time includes the collected data reported by the vehicle at a preset frequency between the current preset time and the previous preset time. The server can extract information from this collected data to obtain the key extraction information corresponding to the current preset time, and store the key extraction information in the database.

[0065] The server can use the key extraction information corresponding to each preset moment within a preset time period stored in the database as diagnostic basis data within the preset time period.

[0066] The following example illustrates this:

[0067] Assuming the regenerative fault prediction method provided in this application is executed once every Sunday, for a given Sunday, the preset time period is from the early morning of the previous Sunday to the early morning of this Sunday. For each vehicle connected to the server network, the server can extract key extraction information corresponding to that vehicle from the database during this period. The key extraction information corresponding to that vehicle during this period includes: key extraction information obtained by extracting information from the data reported by the vehicle on the previous Sunday at a preset frequency on the early morning of Monday of this week; key extraction information obtained by extracting information from the data reported by the vehicle on the previous Monday at a preset frequency on the early morning of Tuesday of this week; ... key extraction information obtained by extracting information from the data reported by the vehicle on the previous Saturday at a preset frequency on the early morning of Sunday of this week. The key extraction information from these days can be used as diagnostic basis data within the preset time period.

[0068] In the above embodiments, each vehicle connected to the server network will report collected data at a preset frequency after startup. The server can extract information from the collected data for subsequent fault mode identification. This information extraction method enables the use of a small amount of data to reflect the vehicle's recurrence fault situation, reduces the amount of data required for subsequent fault mode identification, and improves processing speed.

[0069] In some embodiments, the vehicle operation data to be processed at the current preset time includes the collected data reported by the vehicle at a preset frequency. Information extraction is performed on the vehicle operation data to be processed at the current preset time to obtain key extraction information corresponding to the current preset time. This includes: dividing the collected data reported by the vehicle at a preset frequency into multiple data units according to preset time units; for each data unit, determining the non-regenerative information extraction result based on the collected data contained in the current data unit; determining the regenerative information extraction result based on the inlet temperature of the selective catalytic reduction (SCR) device in the collected data reported by the vehicle at a preset frequency; and determining the key extraction information corresponding to the current preset time based on the non-regenerative information extraction result and the regenerative information extraction result corresponding to each data unit.

[0070] As described above, for each preset moment within a preset time period, the vehicle operation data to be processed at the current preset moment includes the data collected by the vehicle at a preset frequency between the current preset moment and the previous preset moment. The data collected by the vehicle at a preset frequency can be divided into multiple data units according to preset time units, such as 10 minutes.

[0071] For each data unit, the server can determine the non-regenerative information extraction result of the current data unit based on the collected data contained in the current data unit; determine the regenerative information extraction result based on the inlet temperature of the selective catalytic reduction denitrification (SCR) device in the collected data reported by the vehicle at a preset frequency; and use the non-regenerative information extraction result and the regenerative information extraction result corresponding to each data unit as the key extraction information corresponding to the current preset time.

[0072] The above embodiments provide an information extraction method that uses a small amount of data to reflect the vehicle's regeneration fault situation, reducing the amount of data required for subsequent fault mode identification and improving processing speed.

[0073] In some embodiments, the collected data includes: DPF pressure differential of the particulate filter, DPF exhaust volume flow rate, upstream nitrogen oxide sensor reading of the SCR unit, and downstream nitrogen oxide sensor reading of the SCR unit; based on the collected data contained in the current data unit, the non-regenerative information extraction result of the current data unit is determined, including: determining the average value of the DPF pressure differential in each collected data contained in the current data unit to obtain the DPF pressure differential level; determining the first change in DPF pressure differential between two adjacent collected data contained in the current data unit, and determining the total change in DPF based on the first change; determining the difference between the DPF exhaust volume flow rate between two adjacent collected data contained in the current data unit. The second change is used to determine the total change in exhaust volume flow rate. Based on the total change in DPF and the total change in exhaust volume flow rate, the response coefficient of the DPF differential pressure sensor is determined. The sum of the upstream nitrogen oxide sensor readings and the sum of the downstream nitrogen oxide sensor readings in the various collected data included in the current data unit are determined. Based on the sum of the upstream and downstream nitrogen oxide sensor readings, the total conversion efficiency of the SCR device for upstream nitrogen oxides is determined. The non-regenerative information extraction result of the current data unit is determined by combining the DPF differential pressure level, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency of the SCR device for upstream nitrogen oxides.

[0074] The data collected each time a vehicle reports includes: DPF pressure differential, DPF exhaust volume flow rate, upstream nitrogen oxide sensor reading of the SCR unit, and downstream nitrogen oxide sensor reading of the SCR unit.

[0075] For each data unit, the server can calculate the average DPF differential pressure in each of the acquired data contained in the current data unit to obtain the DPF differential pressure level; calculate the first change in DPF differential pressure between two adjacent acquired data in the current data unit, and calculate the sum of each first change to obtain the total DPF change; calculate the second change in DPF exhaust volume flow rate between two adjacent acquired data in the current data unit, and calculate the sum of each second change to obtain the total change in exhaust volume flow rate; calculate the ratio between the total DPF change and the total change in exhaust volume flow rate to obtain the response coefficient of the DPF differential pressure sensor; calculate (the sum of upstream nitrogen oxide sensor readings in each acquired data in the current data unit - the sum of downstream nitrogen oxide sensor readings in each acquired data in the current data unit) / the sum of upstream nitrogen oxide sensor readings in each acquired data in the previous data unit to obtain the total conversion efficiency of the SCR device for upstream nitrogen oxides; and use the DPF differential pressure level, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency of the SCR device for upstream nitrogen oxides as the non-regenerative information extraction results of the current data unit.

[0076] The above embodiments provide a method for obtaining non-regenerative information extraction results. The non-regenerative information extraction results obtained through this method can be used for subsequent fault mode identification, thereby improving the accuracy of regenerative fault prediction.

[0077] In some embodiments, the collected data includes: the inlet temperature of the SCR device; and the determination of regeneration information extraction results based on the inlet temperature of the selective catalytic reduction denitrification SCR device in each collected data reported by the vehicle at a preset frequency, including: determining the time period in which at least one regeneration process occurs based on the inlet temperature of the SCR device in each collected data reported by the vehicle at a preset frequency; determining the average regeneration interval, average regeneration mileage, duration of each regeneration process, and average inlet temperature of the SCR device in the time period corresponding to each regeneration process based on the time period in which at least one regeneration process occurs, and using the determined information as the regeneration information extraction results.

[0078] The regeneration process involves raising the temperature of the after-processor to a certain threshold to oxidize the carbon soot accumulated in the DPF. Therefore, the after-processing temperature during regeneration is relatively high. Consequently, the data reported by the vehicle each time can include the inlet temperature of the SCR device. The server can filter all data reported by the vehicle within a preset time period, selecting data where the inlet temperature of the SCR device is higher than a preset temperature threshold. This data is then used as the data corresponding to the regeneration process. Based on this data, the server can determine the time period during which at least one regeneration process occurs.

[0079] The server, after obtaining the time period of at least one regeneration process, can calculate the interval between two adjacent regeneration processes, and then calculate the average interval to obtain the average regeneration interval. The mileage traveled by the vehicle during two adjacent regeneration processes can be obtained from the mileage recording device, and then averaged to obtain the average regeneration mileage. For each regeneration process, the duration of the regeneration process can be determined based on the start and end times of the time period in which it occurs. For each regeneration process, the inlet temperature of the SCR device can be extracted from the collected data corresponding to that regeneration process, and then averaged to obtain the average inlet temperature of the SCR device during the corresponding time period.

[0080] In the above embodiments, based on the inlet temperature of the SCR device, the collected data corresponding to the regeneration process is selected from all the collected data reported by the vehicle within a preset time period. Based on these data, information such as the average regeneration interval, average regeneration mileage, duration of each regeneration process, and average inlet temperature of the SCR device in the time period corresponding to each regeneration process is determined. This information extraction method enables the use of a small amount of data to reflect the vehicle's regeneration fault status, reduces the amount of data required for subsequent fault mode identification, and improves processing speed.

[0081] In some embodiments, the preset multiple fault modes include a frequent regeneration fault mode, an insufficient regeneration fault mode, a sulfur poisoning fault mode, a water ingress abnormality fault mode, a wiring harness abnormality fault mode, a high soot fault mode, and a multiple ash fault mode; the diagnostic basis data includes: the DPF differential pressure level corresponding to each of the multiple data units, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency; the diagnostic basis data also includes: the average regeneration interval, the average regeneration mileage, the duration of each regeneration process, and the inlet temperature of the SCR device during the time period corresponding to each regeneration process; based on the diagnostic basis data, the flag bits corresponding to each of the preset multiple fault modes are determined, including: judging whether the vehicle has a frequent regeneration abnormality based on at least one of the average regeneration interval or the average regeneration mileage, and determining the flag bit corresponding to the frequent regeneration fault mode based on the judgment result; judging whether the vehicle has insufficient regeneration based on the duration of each regeneration process and the inlet temperature of the SCR device during the time period corresponding to each regeneration process, and determining the flag bit corresponding to the frequent regeneration fault mode based on the judgment result. The system identifies the flag bits corresponding to the insufficient regeneration fault mode; determines whether sulfur poisoning anomalies exist based on the total conversion efficiency of multiple data units, and determines the flag bits corresponding to the sulfur poisoning fault mode based on the judgment results; determines whether the vehicle has DPF water ingress anomalies based on the DPF differential pressure levels corresponding to multiple data units, and determines the flag bits corresponding to the water ingress anomaly fault mode based on the judgment results; determines whether the vehicle has DPF wiring harness anomalies based on the response coefficients of the DPF differential pressure sensors corresponding to multiple data units, and determines the flag bits corresponding to the wiring harness anomaly fault mode based on the judgment results; determines whether the vehicle has high engine carbon soot anomalies based on the DPF differential pressure levels corresponding to multiple data units and the time period of each regeneration process, and determines the flag bits corresponding to the high carbon soot fault mode based on the judgment results; and determines whether the vehicle has multiple ash anomalies based on the DPF differential pressure levels corresponding to multiple data units, the time period of each regeneration process, and the ash threshold, and determines the flag bits corresponding to the multiple ash fault mode based on the judgment results.

[0082] A flag of 1 indicates the presence of an anomaly, while a flag of 0 indicates the absence of an anomaly.

[0083] Specifically, if the average regeneration interval or average regeneration mileage is lower than the corresponding preset threshold, it is determined that there is a frequent regeneration anomaly. Based on this, the flag corresponding to the frequent regeneration failure mode is set to 1. If both the average regeneration interval and the average regeneration mileage are greater than or equal to the corresponding preset threshold, it is determined that there is no frequent regeneration anomaly. Based on this, the flag corresponding to the frequent regeneration failure mode is set to 0.

[0084] Specifically, for each regeneration process, if the inlet temperature of the SCR device is lower than a preset threshold during both the duration of the regeneration process and the corresponding time period, an insufficient regeneration anomaly is determined to exist. Based on this, the flag bit corresponding to the insufficient regeneration fault mode is set to 1. For each regeneration process, if the inlet temperature of the SCR device is greater than or equal to a preset threshold during both the duration of the regeneration process and the corresponding time period, an insufficient regeneration anomaly is determined to exist. Based on this, the flag bit corresponding to the insufficient regeneration fault mode is set to 0.

[0085] Specifically, the process involves acquiring the previous and next data units of the regeneration process, calculating the increase in the total conversion efficiency of the next data unit relative to the previous data unit, and determining that a sulfur poisoning anomaly exists if the increase is greater than a preset threshold. Based on this, the flag corresponding to the sulfur poisoning fault mode is set to 1. If the increase is less than or equal to the preset threshold, it is determined that no sulfur poisoning anomaly exists, and the flag corresponding to the sulfur poisoning fault mode is set to 0.

[0086] Specifically, based on the DPF differential pressure levels corresponding to each of the multiple data units, it is determined whether there is a phenomenon where the DPF differential pressure level changes by more than the corresponding threshold in a short period of time. If so, it is determined that there is a DPF water inlet abnormality. Based on this, the flag bit corresponding to the water inlet abnormality fault mode is set to 1. If not, it is determined that there is no DPF water inlet abnormality. Based on this, the flag bit corresponding to the water inlet abnormality fault mode is set to 0.

[0087] Specifically, if the response coefficients of the DPF differential pressure sensors corresponding to multiple data units are lower than the corresponding threshold, it is determined that there is a DPF harness malfunction. Based on this, the flag bit corresponding to the harness malfunction fault mode is set to 1. If the response coefficients of the DPF differential pressure sensors corresponding to multiple data units are all greater than or equal to the corresponding threshold, it is determined that there is no DPF harness malfunction. Based on this, the flag bit corresponding to the harness malfunction fault mode is set to 0.

[0088] Specifically, for each regeneration process, the preceding and following data units of the regeneration process are acquired. If the DPF differential pressure level of the following data unit is lower than that of the preceding data unit and the difference is greater than a preset threshold, it is determined that there is an abnormality of high carbon soot in the engine. Based on this, the flag bit corresponding to the high carbon soot fault mode is set to 1; otherwise, the flag bit corresponding to the high carbon soot fault mode is set to 0.

[0089] Specifically, for each regeneration process, the data units following the regeneration process are determined. If the DPF differential pressure levels of these data units are all greater than or equal to the corresponding threshold, it is determined that there are multiple ash anomalies. Based on this, the flag bit corresponding to the multiple ash failure mode is set to 1; otherwise, the flag bit corresponding to the multiple ash failure mode is set to 0.

[0090] The above embodiments provide a specific implementation of the fault identification mode. The identification results can be used to determine the recurrence fault prediction results, so as to predict the recurrence fault in advance for the vehicle owner and ensure the vehicle driving safety.

[0091] In some embodiments, the validity analysis of each flag bit in the vehicle-related fault code includes: if all flag bits in the vehicle-related fault code that indicate an abnormality for the water ingress fault mode, the high carbon soot fault mode, and the multiple ash fault mode are indicated as abnormal, then the flag bit corresponding to the water ingress fault mode is determined to be valid, while the flag bits corresponding to the high carbon soot fault mode and the multiple ash fault mode are invalid; if all flag bits in the vehicle-related fault code that indicate an abnormality for the wiring harness fault mode and the multiple ash fault mode are indicated as abnormal, then the flag bit corresponding to the wiring harness fault mode is determined to be valid, while the flag bit corresponding to the multiple ash fault mode is invalid; if all flag bits in the vehicle-related fault code that indicate an abnormality for the multiple ash fault mode and the high carbon soot fault mode are indicated as abnormal, then the flag bit corresponding to the multiple ash fault mode is determined to be valid, while the flag bit corresponding to the high carbon soot fault mode is invalid.

[0092] After obtaining the flag bits corresponding to each of the preset fault modes, these flag bits can be arranged in a certain order to obtain the corresponding vehicle fault code. Once the fault code is obtained, its validity can be analyzed.

[0093] The server can determine the number of flags with a value of 1 in the exception code. If the number is greater than or equal to 2, the exception code will then be analyzed for validity.

[0094] In the exception code, if there are two or more flags with a value of 1, it can be determined whether the flags with a value of 1 include the flags corresponding to the water ingress fault mode, the high carbon soot fault mode, and the high ash fault mode. If so, considering that water ingress into the DPF differential pressure sensor increases the likelihood of the high engine carbon soot and high DPF ash fault modes being misjudged as abnormal, the flags corresponding to the water ingress fault mode in the exception code are considered valid, while the flags corresponding to the high carbon soot and high ash fault modes are considered invalid. Alternatively, it can be determined whether the flags with a value of 1 include the flags corresponding to the wiring harness fault mode and the high ash fault mode. If so, considering that the high DPF ash fault mode is more likely to be misjudged as abnormal when there is an anomaly in the DPF wiring harness, the flags corresponding to the wiring harness fault mode are considered valid, while the flags corresponding to the high ash fault mode are considered invalid. Alternatively, it can be determined whether the flags with a value of 1 include the flags corresponding to the high ash content fault mode and the high soot fault mode. If they do, considering that the high soot mode is more likely to be misjudged as abnormal when the DPF has a high ash content, it can be determined that the flags corresponding to the high ash content fault mode are valid and the flags corresponding to the high soot fault mode are invalid.

[0095] The above embodiments provide a specific process for flag validity analysis. This process invalidates flags that are likely to be misjudged, which can more accurately locate the root cause of the fault and improve the accuracy of fault location.

[0096] In some embodiments of the regenerative fault prediction method provided in this application, see [link to relevant documentation]. Figure 3As shown, the process includes the following steps: 1. Vehicle-to-everything (V2X) data collection. The server receives the collected data reported by the vehicles. See the description above for details. 2. Daily information extraction algorithm operation. Information is extracted from the collected data received the previous day at midnight each day to obtain key extraction information. See the description above for details. 3. Periodic anomaly identification algorithm operation. When the anomaly identification algorithm is to be run, the key extraction information from the last run of the algorithm to the present is used as diagnostic basis data. Anomaly codes are determined based on this diagnostic basis data. See the description above for details. 4. Intelligent fault mode decision-making based on anomaly information. False diagnoses may occur in the flag bits of the anomaly code; therefore, validity analysis is required. See the description above for the process of validity analysis of each flag bit in the anomaly code. 5. Outputting fault diagnosis results. After receiving the updated anomaly code, the server extracts flag bits with values ​​of a first preset value from the updated anomaly code and obtains the corresponding fault modes. Based on these fault modes, the recurrence fault prediction results for the vehicle are determined. See the description above for details.

[0097] In some embodiments, see Figure 4 As shown, the information extraction process can include extracting information such as the vehicle's DPF differential pressure level, the response coefficient of the vehicle's DPF differential pressure sensor, the vehicle's SCR efficiency, and the vehicle's regeneration status. Detailed implementation methods are described above. Abnormal mode diagnosis can include fault modes such as abnormal regeneration frequency, insufficient regeneration, sulfur poisoning, water ingress in the DPF differential pressure sensor, abnormal DPF differential pressure sensor wiring harness, high engine soot levels, and multiple DPF ash content anomalies. Specific diagnostic methods for each of these fault modes are described above. Abnormal phenomenon coupling correction is the effectiveness analysis mentioned above. If the DPF differential pressure sensor water ingress anomaly flag is 1, the high engine soot anomaly flag is 1, and the multiple DPF ash content anomaly flag is 1, the flags can be updated to: if the DPF differential pressure sensor water ingress anomaly flag is 1, the high engine soot anomaly flag is 0, and the multiple DPF ash content anomaly flag is 0. Detailed implementation methods are described above. It can output maintenance suggestions based on the results of abnormal phenomena and coupled correction. For example, if the abnormal water ingress flag of the DPF differential pressure sensor is 1, the maintenance suggestion is: the DPF differential pressure sensor is ingressing water, and it is recommended to disassemble and drain it.

[0098] It should be understood that although the steps in the flowcharts of the above embodiments are shown sequentially according to the arrows, these steps are not necessarily executed in the order indicated by the arrows. Unless explicitly stated herein, there is no strict order restriction on the execution of these steps, and they can be executed in other orders. Moreover, at least some steps in the flowcharts of the above embodiments may include multiple steps or multiple stages. These steps or stages are not necessarily completed at the same time, but can be executed at different times. The execution order of these steps or stages is not necessarily sequential, but can be performed alternately or in turn with other steps or at least some of the steps or stages of other steps.

[0099] Based on the same inventive concept, this application also provides a regenerative fault prediction device for implementing the regenerative fault prediction method described above. The solution provided by this device is similar to the solution described in the above method; therefore, the specific limitations in one or more regenerative fault prediction device embodiments provided below can be found in the limitations of the regenerative fault prediction method described above, and will not be repeated here.

[0100] In one embodiment, such as Figure 5 As shown, a regenerative fault prediction device is provided, comprising:

[0101] The acquisition module 501 is used to acquire diagnostic basis data within a preset time period. The diagnostic basis data is extracted based on the vehicle operation data reported by the vehicle within the preset time period.

[0102] The determination module 502 is used to determine the flag bits corresponding to each of the preset multiple fault modes based on diagnostic data. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0103] The determination module 502 is also used to determine the abnormal code corresponding to the vehicle according to the flag bits corresponding to each of the preset multiple fault modes, and to perform validity analysis on each flag bit in the abnormal code corresponding to the vehicle, and update the abnormal code based on the validity analysis results to obtain the updated abnormal code.

[0104] The determination module 502 is also used to determine the cause of the vehicle's regeneration failure based on the updated exception code.

[0105] In some embodiments, the acquisition module 501 is further configured to: determine the vehicle operation data to be processed at each preset moment within a preset time period, extract information from the vehicle operation data to be processed at the current preset moment, obtain key extraction information corresponding to the current preset moment, store the key extraction information, and use the stored key extraction information corresponding to each preset moment as diagnostic basis data within the preset time period.

[0106] In some embodiments, the vehicle operation data to be processed at the current preset time includes the collected data reported by the vehicle at a preset frequency. The acquisition module 501 is further configured to: divide the collected data reported by the vehicle at a preset frequency into multiple data units according to preset time units; for each data unit, determine the non-regenerative information extraction result of the current data unit based on the collected data contained in the current data unit; determine the regenerative information extraction result based on the inlet temperature of the selective catalytic reduction denitrification (SCR) device in the collected data reported by the vehicle at a preset frequency; and determine the key extraction information corresponding to the current preset time based on the non-regenerative information extraction result and the regenerative information extraction result corresponding to each data unit.

[0107] In some embodiments, the collected data includes: DPF pressure differential of the particulate filter, DPF exhaust volume flow rate, upstream nitrogen oxide sensor reading of the SCR device, and downstream nitrogen oxide sensor reading of the SCR device; the acquisition module 501 is further configured to: determine the average value of the DPF pressure differential in each collected data contained in the current data unit to obtain the DPF pressure differential level; determine a first change in the DPF pressure differential between two adjacent collected data contained in the current data unit, and determine the total DPF change based on the first change; determine a second change in the DPF exhaust volume flow rate between two adjacent collected data contained in the current data unit, and determine the total DPF change based on the second change. Determine the total change in exhaust volume flow rate; based on the total change in DPF and the total change in exhaust volume flow rate, determine the response coefficient of the DPF differential pressure sensor; determine the sum of the upstream nitrogen oxide sensor readings and the sum of the downstream nitrogen oxide sensor readings in the various collected data included in the current data unit; based on the sum of the upstream and downstream nitrogen oxide sensor readings, determine the total conversion efficiency of the SCR device for upstream nitrogen oxides; combine the DPF differential pressure level, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency of the SCR device for upstream nitrogen oxides to determine the non-regenerative information extraction result of the current data unit.

[0108] In some embodiments, the collected data includes the inlet temperature of the SCR device. The acquisition module 501 is further configured to: determine the time period in which at least one regeneration process occurs based on the inlet temperature of the SCR device in each collected data reported by the vehicle at a preset frequency; determine the average regeneration interval, average regeneration mileage, duration of each regeneration process, and average inlet temperature of the SCR device in the time period corresponding to each regeneration process based on the time period in which at least one regeneration process occurs; and use the determined information as the regeneration information extraction result.

[0109] In some embodiments, the preset multiple fault modes include a frequent regeneration fault mode, an insufficient regeneration fault mode, a sulfur poisoning fault mode, a water ingress fault mode, a wiring harness abnormality fault mode, a high soot fault mode, and a multiple ash fault mode; the diagnostic basis data includes: the DPF differential pressure level corresponding to each of the multiple data units, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency; the diagnostic basis data also includes: the average regeneration interval, the average regeneration mileage, the duration of each regeneration process, and the inlet temperature of the SCR device during the time period corresponding to each regeneration process; the determination module 502 is specifically used to: determine whether the vehicle has a frequent regeneration abnormality based on at least one of the average regeneration interval or the average regeneration mileage, and determine the flag bit corresponding to the frequent regeneration fault mode based on the determination result; determine whether the vehicle has an insufficient regeneration abnormality based on the duration of each regeneration process and the inlet temperature of the SCR device during the time period corresponding to each regeneration process, and determine the insufficient regeneration fault mode based on the determination result. The system determines the following: First, it identifies the corresponding flag bit. Second, it determines whether sulfur poisoning is present based on the total conversion efficiency of each data unit, and determines the flag bit corresponding to the sulfur poisoning fault mode. Third, it identifies whether the vehicle has DPF water ingress anomalies based on the DPF differential pressure levels of each data unit, and determines the flag bit corresponding to the water ingress anomaly fault mode. Fourth, it identifies whether the vehicle has DPF wiring harness anomalies based on the response coefficients of the DPF differential pressure sensors of each data unit, and determines the flag bit corresponding to the wiring harness anomaly fault mode. Fifth, it identifies whether the vehicle has high engine soot anomalies based on the DPF differential pressure levels of each data unit and the time period of each regeneration process, and determines the flag bit corresponding to the high soot fault mode. Sixth, it identifies whether the vehicle has multiple ash anomalies based on the DPF differential pressure levels of each data unit, the time period of each regeneration process, and the ash threshold, and determines the flag bit corresponding to the multiple ash fault mode.

[0110] In some embodiments, the determining module 502 is specifically configured to: determine that the flag bit corresponding to the water ingress fault mode is valid and the flag bits corresponding to the high carbon soot fault mode and the flag bits corresponding to the multiple ash fault mode are invalid when all flag bits in the fault code corresponding to the vehicle indicate an abnormality; determine that the flag bit corresponding to the wiring harness fault mode is valid and the flag bit corresponding to the multiple ash fault mode is invalid when all flag bits in the fault code corresponding to the vehicle indicate an abnormality; and determine that the flag bit corresponding to the multiple ash fault mode is valid and the flag bit corresponding to the high carbon soot fault mode is invalid when all flag bits in the fault code corresponding to the vehicle indicate an abnormality.

[0111] Each module in the aforementioned regenerative fault prediction device can be implemented entirely or partially through software, hardware, or a combination thereof. These modules can be embedded in or independent of the processor in a computer device, or stored in the memory of a computer device as software, so that the processor can call and execute the corresponding operations of each module.

[0112] In one embodiment, a computer device is provided, which may be a server, and its internal structure diagram may be as follows: Figure 6 As shown, the computer device includes a processor, memory, and a network interface connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The database stores data. The network interface communicates with external terminals via a network connection. When executed by the processor, the computer program implements a regenerative fault prediction method.

[0113] Those skilled in the art will understand that Figure 6 The structure shown is merely a block diagram of a portion of the structure related to the present application and does not constitute a limitation on the computer device to which the present application is applied. Specific computer devices may include more or fewer components than those shown in the figure, or combine certain components, or have different component arrangements.

[0114] In one embodiment, a computer device is provided, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to perform the following steps:

[0115] Obtain diagnostic data within a preset time period. The diagnostic data is extracted from the vehicle operation data reported by the vehicle within the preset time period.

[0116] Based on diagnostic data, flag bits corresponding to each of the preset fault modes are determined. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0117] Based on the flag bits corresponding to each of the multiple preset fault modes, the corresponding abnormal code of the vehicle is determined, and the validity analysis of each flag bit in the corresponding abnormal code of the vehicle is performed. Based on the results of the validity analysis, the abnormal code is updated to obtain the updated abnormal code.

[0118] Based on the updated anomaly code, the regenerative fault prediction result is determined.

[0119] In one embodiment, when the processor executes the computer program, it further performs the following steps: at each preset moment within a preset time period, it determines the vehicle operation data that needs to be processed at the current preset moment, extracts information from the vehicle operation data that needs to be processed at the current preset moment, obtains key extraction information corresponding to the current preset moment, and stores the key extraction information; and uses the stored key extraction information corresponding to each preset moment as diagnostic basis data within the preset time period.

[0120] In one embodiment, the vehicle operation data to be processed at the current preset time includes the collected data reported by the vehicle at a preset frequency. When the processor executes the computer program, it also performs the following steps: dividing the collected data reported by the vehicle at the preset frequency into multiple data units according to preset time units; for each data unit, determining the non-regenerative information extraction result of the current data unit based on the collected data contained in the current data unit; determining the regenerative information extraction result based on the inlet temperature of the selective catalytic reduction denitrification (SCR) device in the collected data reported by the vehicle at the preset frequency; and determining the key extraction information corresponding to the current preset time based on the non-regenerative information extraction result and the regenerative information extraction result corresponding to each data unit.

[0121] In one embodiment, the collected data includes: DPF pressure differential of the particulate filter, DPF exhaust volume flow rate, upstream nitrogen oxide sensor reading of the SCR unit, and downstream nitrogen oxide sensor reading of the SCR unit; when the processor executes the computer program, it further performs the following steps: determining the average value of the DPF pressure differential in each collected data contained in the current data unit to obtain the DPF pressure differential level; determining a first change in the DPF pressure differential between two adjacent collected data contained in the current data unit, and determining the total DPF change based on the first change; determining a second change in the DPF exhaust volume flow rate between two adjacent collected data contained in the current data unit, and determining the total DPF change based on the second change. The total change in exhaust volume flow rate is determined by the change in DPF and exhaust volume flow rate. Based on this total change in DPF and exhaust volume flow rate, the response coefficient of the DPF differential pressure sensor is determined. The sum of the upstream and downstream nitrogen oxide sensor readings in the current data unit is determined. Based on this sum, the total conversion efficiency of the SCR device for upstream nitrogen oxides is determined. The non-regenerative information extraction result of the current data unit is determined by combining the DPF differential pressure level, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency of the SCR device for upstream nitrogen oxides.

[0122] In one embodiment, the collected data includes the inlet temperature of the SCR device. When the processor executes the computer program, it further performs the following steps: based on the inlet temperature of the SCR device in each collected data reported by the vehicle at a preset frequency, it determines the time period in which at least one regeneration process occurs; based on the time period in which at least one regeneration process occurs, it determines the average regeneration interval, the average regeneration mileage, the duration of each regeneration process, and the average inlet temperature of the SCR device in the time period corresponding to each regeneration process, and uses the determined information as the regeneration information extraction result.

[0123] In one embodiment, the preset multiple fault modes include a frequent regeneration fault mode, an insufficient regeneration fault mode, a sulfur poisoning fault mode, a water ingress abnormality fault mode, a wiring harness abnormality fault mode, a high soot fault mode, and a multiple ash fault mode; the diagnostic basis data includes: the DPF differential pressure level corresponding to each of the multiple data units, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency; the diagnostic basis data also includes: the average regeneration interval, the average regeneration mileage, the duration of each regeneration process, and the inlet temperature of the SCR device during the time period corresponding to each regeneration process; when the processor executes the computer program, it also performs the following steps: based on at least one of the average regeneration interval or the average regeneration mileage, it determines whether the vehicle has a frequent regeneration abnormality, and determines the flag bit corresponding to the frequent regeneration fault mode based on the determination result; based on the duration of each regeneration process and the inlet temperature of the SCR device during the time period corresponding to each regeneration process, it determines whether the vehicle has an insufficient regeneration abnormality, and determines the insufficient regeneration based on the determination result. The system identifies the following flags for different fault modes: First, based on the total conversion efficiency of each data unit, it determines whether sulfur poisoning is present and determines the flag for the sulfur poisoning fault mode. Second, based on the DPF differential pressure levels of each data unit, it determines whether the vehicle has DPF water ingress fault mode and determines the flag for the water ingress fault mode. Third, based on the response coefficients of the DPF differential pressure sensors of each data unit, it determines whether the vehicle has DPF wiring harness fault mode and determines the flag for the wiring harness fault mode. Fourth, based on the DPF differential pressure levels of each data unit and the time period of each regeneration process, it determines whether the vehicle has high engine soot fault mode and determines the flag for the high soot fault mode. Fifth, based on the DPF differential pressure levels of each data unit, the time period of each regeneration process, and the ash threshold, it determines whether the vehicle has multiple ash fault modes and determines the flag for the multiple ash fault modes.

[0124] In one embodiment, when the processor executes the computer program, it further implements the following steps: if all the flag bits in the vehicle-corresponding error code indicate an error, such as the flag bit corresponding to the water ingress error fault mode, the flag bit corresponding to the high carbon soot fault mode, and the flag bit corresponding to the multiple ash fault mode, then the flag bit corresponding to the water ingress error fault mode is determined to be valid, while the flag bits corresponding to the high carbon soot fault mode and the multiple ash fault mode are invalid; if all the flag bits in the vehicle-corresponding error code indicate an error, such as the flag bit corresponding to the wiring harness error fault mode and the flag bit corresponding to the multiple ash fault mode, then the flag bit corresponding to the wiring harness error fault mode is determined to be valid, while the flag bit corresponding to the multiple ash fault mode is invalid; if all the flag bits in the vehicle-corresponding error code indicate an error, such as the flag bit corresponding to the multiple ash fault mode and the flag bit corresponding to the high carbon soot fault mode, then the flag bit corresponding to the multiple ash fault mode is determined to be valid, while the flag bit corresponding to the high carbon soot fault mode is invalid.

[0125] In one embodiment, a computer-readable storage medium is provided having a computer program stored thereon, the computer program performing the following steps when executed by a processor:

[0126] Obtain diagnostic data within a preset time period. The diagnostic data is extracted from the vehicle operation data reported by the vehicle within the preset time period.

[0127] Based on diagnostic data, flag bits corresponding to each of the preset fault modes are determined. The flag bits are used to indicate whether there is an abnormality in the vehicle under the corresponding fault mode.

[0128] Based on the flag bits corresponding to each of the multiple preset fault modes, the corresponding abnormal code of the vehicle is determined, and the validity analysis of each flag bit in the corresponding abnormal code of the vehicle is performed. Based on the results of the validity analysis, the abnormal code is updated to obtain the updated abnormal code.

[0129] Based on the updated anomaly code, the regenerative fault prediction result is determined.

[0130] In one embodiment, when the computer program is executed by the processor, it further performs the following steps: at each preset moment within a preset time period, determining the vehicle operation data that needs to be processed at the current preset moment, extracting information from the vehicle operation data that needs to be processed at the current preset moment, obtaining key extraction information corresponding to the current preset moment, and storing the key extraction information; using the stored key extraction information corresponding to each preset moment as diagnostic basis data within the preset time period.

[0131] In one embodiment, the vehicle operation data to be processed at the current preset time includes the collected data reported by the vehicle at a preset frequency. When the computer program is executed by the processor, it further implements the following steps: dividing the collected data reported by the vehicle at the preset frequency into multiple data units according to preset time units; for each data unit, determining the non-regenerative information extraction result of the current data unit based on the collected data contained in the current data unit; determining the regenerative information extraction result based on the inlet temperature of the selective catalytic reduction denitrification (SCR) device in the collected data reported by the vehicle at the preset frequency; and determining the key extraction information corresponding to the current preset time based on the non-regenerative information extraction result and the regenerative information extraction result corresponding to each data unit.

[0132] In one embodiment, the collected data includes: DPF pressure differential of the particulate filter, DPF exhaust volume flow rate, upstream nitrogen oxide sensor reading of the SCR unit, and downstream nitrogen oxide sensor reading of the SCR unit; when the computer program is executed by the processor, it further performs the following steps: determining the average value of the DPF pressure differential in each collected data contained in the current data unit to obtain the DPF pressure differential level; determining a first change in the DPF pressure differential between two adjacent collected data contained in the current data unit, and determining the total DPF change based on the first change; determining a second change in the DPF exhaust volume flow rate between two adjacent collected data contained in the current data unit, and determining the total DPF change based on the second change. The total change in exhaust volume flow rate is determined by the change in DPF and exhaust volume flow rate. Based on this total change in DPF and exhaust volume flow rate, the response coefficient of the DPF differential pressure sensor is determined. The sum of the upstream and downstream nitrogen oxide sensor readings in the current data unit is determined. Based on this sum, the total conversion efficiency of the SCR device for upstream nitrogen oxides is determined. The non-regenerative information extraction result of the current data unit is determined by combining the DPF differential pressure level, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency of the SCR device for upstream nitrogen oxides.

[0133] In one embodiment, the collected data includes the inlet temperature of the SCR device. When the computer program is executed by the processor, it further performs the following steps: based on the inlet temperature of the SCR device in each collected data reported by the vehicle at a preset frequency, determine the time period in which at least one regeneration process occurs; based on the time period in which at least one regeneration process occurs, determine the average regeneration interval, the average regeneration mileage, the duration of each regeneration process, and the average inlet temperature of the SCR device in the time period corresponding to each regeneration process, and use the determined information as the regeneration information extraction result.

[0134] In one embodiment, the preset multiple fault modes include a frequent regeneration fault mode, an insufficient regeneration fault mode, a sulfur poisoning fault mode, a water ingress abnormality fault mode, a wiring harness abnormality fault mode, a high soot fault mode, and a multiple ash fault mode; the diagnostic basis data includes: the DPF differential pressure level corresponding to each of the multiple data units, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency; the diagnostic basis data also includes: the average regeneration interval, the average regeneration mileage, the duration of each regeneration process, and the inlet temperature of the SCR device during the time period corresponding to each regeneration process; when the computer program is executed by the processor, it further implements the following steps: based on at least one of the average regeneration interval or the average regeneration mileage, determine whether the vehicle has a frequent regeneration abnormality, and determine the flag bit corresponding to the frequent regeneration fault mode based on the determination result; based on the duration of each regeneration process and the inlet temperature of the SCR device during the time period corresponding to each regeneration process, determine whether the vehicle has an insufficient regeneration abnormality, and determine the insufficient regeneration based on the determination result. The system uses the following methods to determine the fault modes: First, it identifies the corresponding flag bits for each fault mode. Second, it determines whether there is a sulfur poisoning anomaly based on the total conversion efficiency of each data unit, and determines the flag bits corresponding to the sulfur poisoning fault mode. Third, it identifies whether there is a DPF water ingress anomaly based on the DPF differential pressure levels of each data unit, and determines the flag bits corresponding to the water ingress anomaly fault mode. Fourth, it identifies whether there is a DPF wiring harness anomaly based on the response coefficients of the DPF differential pressure sensors of each data unit, and determines the flag bits corresponding to the wiring harness anomaly fault mode. Fifth, it identifies whether there is an engine high soot anomaly based on the DPF differential pressure levels of each data unit and the time period of each regeneration process, and determines the flag bits corresponding to the high soot fault mode. Sixth, it identifies whether there are multiple ash anomalies based on the DPF differential pressure levels of each data unit, the time period of each regeneration process, and the ash threshold, and determines the flag bits corresponding to the multiple ash fault modes.

[0135] In one embodiment, when the computer program is executed by the processor, it further implements the following steps: if all the flag bits in the vehicle-corresponding error code indicate an error, such as the flag bit corresponding to the water ingress error fault mode, the flag bit corresponding to the high carbon soot fault mode, and the flag bit corresponding to the multiple ash fault mode, then the flag bit corresponding to the water ingress error fault mode is determined to be valid, while the flag bits corresponding to the high carbon soot fault mode and the multiple ash fault mode are invalid; if all the flag bits in the vehicle-corresponding error code indicate an error, such as the flag bit corresponding to the wiring harness error fault mode and the flag bit corresponding to the multiple ash fault mode, then the flag bit corresponding to the wiring harness error fault mode is determined to be valid, while the flag bit corresponding to the multiple ash fault mode is invalid; if all the flag bits in the vehicle-corresponding error code indicate an error, such as the flag bit corresponding to the multiple ash fault mode and the flag bit corresponding to the high carbon soot fault mode, then the flag bit corresponding to the multiple ash fault mode is determined to be valid, while the flag bit corresponding to the high carbon soot fault mode is invalid.

[0136] In one embodiment, a computer program product is provided, including a computer program that, when executed by a processor, implements the method provided in any of the above embodiments.

[0137] Those skilled in the art will understand that all or part of the processes in the above embodiments can be implemented by a computer program instructing related hardware. The computer program can be stored in a non-volatile computer-readable storage medium. When executed, the computer program can include the processes of the embodiments described above. Any references to memory, databases, or other media used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetic random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can take many forms, such as Static Random Access Memory (SRAM) or Dynamic Random Access Memory (DRAM). The databases involved in the embodiments provided in this application may include at least one type of relational database and non-relational database. Non-relational databases may include, but are not limited to, blockchain-based distributed databases. The processors involved in the embodiments provided in this application may be general-purpose processors, central processing units, graphics processing units, digital signal processors, programmable logic devices, quantum computing-based data processing logic devices, etc., and are not limited to these.

[0138] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0139] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are specific and detailed, they should not be construed as limiting the scope of this patent application. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this application should be determined by the appended claims.

Claims

1. A method for predicting regenerative faults, characterized in that, The method includes: Obtain diagnostic basis data within a preset time period, wherein the diagnostic basis data is extracted based on vehicle operation data reported by the vehicle within the preset time period; Based on the diagnostic data, a flag bit corresponding to each of the preset multiple fault modes is determined. The flag bit is used to indicate whether the vehicle has an abnormality in the corresponding fault mode. The preset multiple fault modes include at least one of the following: frequent regeneration fault mode, insufficient regeneration fault mode, sulfur poisoning fault mode, water ingress fault mode, wiring harness abnormality fault mode, high carbon soot fault mode, and multiple ash fault mode. Based on the flag bits corresponding to the preset multiple fault modes, the abnormal code corresponding to the vehicle is determined, and the validity analysis of each flag bit in the abnormal code corresponding to the vehicle is performed. Based on the validity analysis results, the abnormal code is updated to obtain the updated abnormal code. The validity analysis of each flag bit in the abnormal code corresponding to the vehicle includes: If all the flags in the fault code corresponding to the water ingress fault mode, the high carbon soot fault mode, and the multiple ash fault mode indicate that there is an abnormality, then the flags in the water ingress fault mode are valid, and the flags in the high carbon soot fault mode and the multiple ash fault mode are invalid. If both the flag bit corresponding to the wiring harness abnormality fault mode and the flag bit corresponding to the ash multi-fault mode in the flag bits included in the abnormal code corresponding to the vehicle indicate that there is an abnormality, then it is determined that the flag bit corresponding to the wiring harness abnormality fault mode is valid and the flag bit corresponding to the ash multi-fault mode is invalid. If the flag bit corresponding to the ash content multi-fault mode and the flag bit corresponding to the carbon soot high-fault mode in the abnormal code of the vehicle are abnormal, then the flag bit corresponding to the ash content multi-fault mode is determined to be valid and the flag bit corresponding to the carbon soot high-fault mode is determined to be invalid. Based on the updated anomaly code, the regeneration fault prediction result is determined.

2. The method according to claim 1, characterized in that, Before acquiring diagnostic data within a preset time period, the method further includes: At each preset moment within the preset time period, determine the vehicle operation data that needs to be processed at the current preset moment, extract information from the vehicle operation data that needs to be processed at the current preset moment, obtain the key extraction information corresponding to the current preset moment, and store the key extraction information. The acquisition of diagnostic data within a preset time period includes: The key extraction information corresponding to each preset time point is stored as the diagnostic basis data within the preset time period.

3. The method according to claim 2, characterized in that, The vehicle operation data to be processed at the current preset time includes the collected data reported by the vehicles at a preset frequency. The step of extracting information from the vehicle operation data to be processed at the current preset time to obtain key extracted information corresponding to the current preset time includes: The collected data reported by the vehicle at a preset frequency is divided into multiple data units according to a preset time unit. For each data unit, the non-regenerative information extraction result of the current data unit is determined based on the collected data contained in the current data unit. Based on the inlet temperature of the selective catalytic reduction (SCR) device in the data collected by the vehicle at a preset frequency, the regeneration information extraction result is determined. Based on the non-regenerated information extraction results corresponding to each data unit and the regenerated information extraction results, the key extraction information corresponding to the current preset time is determined.

4. The method according to claim 3, characterized in that, The collected data includes: DPF pressure differential, DPF exhaust volume flow rate, upstream nitrogen oxide sensor reading of the SCR unit, and downstream nitrogen oxide sensor reading of the SCR unit; the determination of the non-regenerative information extraction result of the current data unit based on the collected data includes: Determine the average value of the DPF differential pressure in each collected data set contained in the current data unit to obtain the DPF differential pressure level; Determine the first change in DPF differential pressure between two adjacent data points in the current data unit, and determine the total change in DPF based on the first change; determine the second change in DPF exhaust volume flow rate between two adjacent data points in the current data unit, and determine the total change in exhaust volume flow rate based on the second change; determine the response coefficient of the DPF differential pressure sensor based on the total change in DPF and the total change in exhaust volume flow rate. The sum of the upstream nitrogen oxide sensor readings and the sum of the downstream nitrogen oxide sensor readings in each of the collected data contained in the current data unit are determined. Based on the sum of the upstream nitrogen oxide sensor readings and the sum of the downstream nitrogen oxide sensor readings, the total conversion efficiency of the SCR device for upstream nitrogen oxides is determined. The non-regenerative information extraction result of the current data unit is determined by the DPF differential pressure level, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency of the SCR device for upstream nitrogen oxides.

5. The method according to claim 3, characterized in that, The collected data includes: the inlet temperature of the SCR device. The determination of regeneration information extraction results based on the inlet temperature of the selective catalytic reduction denitrification SCR device from the collected data reported by the vehicle at a preset frequency includes: Based on the inlet temperature of the SCR device in each collected data reported by the vehicle at a preset frequency, determine the time period during which at least one regeneration process occurs. Based on the time period during which the at least one regeneration process occurs, the average regeneration interval, average regeneration mileage, duration of each regeneration process, and average inlet temperature of the SCR device during the time period corresponding to each regeneration process are determined, and the determined information is used as the regeneration information extraction result.

6. The method according to claim 1, characterized in that, The preset multiple fault modes include frequent regeneration fault mode, insufficient regeneration fault mode, sulfur poisoning fault mode, abnormal water ingress fault mode, abnormal wiring harness fault mode, high carbon soot fault mode, and high ash content fault mode. The diagnostic data includes: the DPF differential pressure level corresponding to each of the multiple data units, the response coefficient of the DPF differential pressure sensor, and the total conversion efficiency; the diagnostic data also includes: the average regeneration interval, the average regeneration mileage, the duration of each regeneration process, and the inlet temperature of the SCR device during the time period corresponding to each regeneration process. The step of determining the flag bits corresponding to each of the preset multiple fault modes based on the diagnostic data includes: Based on at least one of the average regeneration interval or average regeneration mileage, determine whether the vehicle has a frequent regeneration anomaly, and determine the flag bit corresponding to the frequent regeneration fault mode based on the determination result; Based on the duration of each regeneration process and the inlet temperature of the SCR device during the time period corresponding to each regeneration process, it is determined whether the vehicle has an insufficient regeneration abnormality, and the flag bit corresponding to the insufficient regeneration fault mode is determined based on the judgment result. Based on the total conversion efficiency of each of the multiple data units, determine whether there is a sulfur poisoning anomaly, and determine the flag bit corresponding to the sulfur poisoning fault mode based on the judgment result. Based on the DPF differential pressure levels corresponding to each of the multiple data units, it is determined whether the vehicle has a DPF water ingress anomaly, and the flag bit corresponding to the water ingress anomaly fault mode is determined based on the determination result. Based on the response coefficients of the DPF differential pressure sensors corresponding to each of the multiple data units, it is determined whether the vehicle has a DPF wiring harness abnormality, and the flag bit corresponding to the wiring harness abnormality fault mode is determined based on the determination result. Based on the DPF differential pressure level corresponding to each of the multiple data units and the time period of each regeneration process, it is determined whether the vehicle has an engine carbon soot high anomaly, and the flag bit corresponding to the high carbon soot fault mode is determined based on the judgment result. Based on the DPF differential pressure level corresponding to each of the multiple data units, the time period of each regeneration process, and the ash content threshold, it is determined whether the vehicle has multiple ash content anomalies, and the flag bit corresponding to the multiple ash content fault mode is determined based on the judgment result.

7. A regenerative fault prediction device, characterized in that, The device includes: The acquisition module is used to acquire diagnostic basis data within a preset time period. The diagnostic basis data is extracted based on the vehicle operation data reported by the vehicle within the preset time period. The determination module is used to determine the flag bits corresponding to each of the preset multiple fault modes based on the diagnostic basis data. The flag bits are used to indicate whether the vehicle has an abnormality in the corresponding fault mode. The preset multiple fault modes include at least one of the following: frequent regeneration fault mode, insufficient regeneration fault mode, sulfur poisoning fault mode, water ingress abnormal fault mode, wiring harness abnormal fault mode, high carbon soot fault mode, and multiple ash fault mode. The determining module is further configured to determine the abnormal code corresponding to the vehicle based on the flag bits corresponding to each of the preset multiple fault modes, and to perform validity analysis on each flag bit in the abnormal code corresponding to the vehicle, and update the abnormal code based on the validity analysis results to obtain an updated abnormal code; the validity analysis on each flag bit in the abnormal code corresponding to the vehicle includes: if the flag bits corresponding to the water ingress abnormal fault mode, the flag bits corresponding to the high carbon soot fault mode, and the flag bits corresponding to the multiple ash content fault modes in the abnormal code corresponding to the vehicle all indicate an abnormality, then the flag bit corresponding to the water ingress abnormal fault mode is determined. If the flags corresponding to the high carbon soot fault mode and the high ash soot fault mode are both valid, and the flags corresponding to the high ash soot fault mode are invalid, then if all the flags in the fault code for the vehicle indicate an abnormality, the flag corresponding to the high carbon soot fault mode is valid, and the flag corresponding to the high carbon soot fault mode is invalid. The determining module is further configured to determine the cause of the vehicle's regeneration failure based on the updated exception code.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 6.

Images