A vehicle diagnosis and control method and device based on a thermal management system, an electronic device, and a storage medium

Abstract

The application discloses a vehicle diagnosis and control method based on a thermal management system. The method performs clustering processing on a plurality of sample vehicles based on state data of the plurality of sample vehicles, obtains a primary clustering and a plurality of secondary clusterings of each primary clustering, and determines a standard optimal energy consumption model of each secondary clustering. According to the standard optimal energy consumption model, a current attenuation factor of a target vehicle is calculated when the target vehicle has an implicit fault, and a current health level of the target vehicle is determined according to the current attenuation factor. According to the historical attenuation factor and the current attenuation factor of the target vehicle, future attenuation of the target vehicle is predicted. Based on the current health level of the target vehicle, a thermal management compensation strategy is generated for the target vehicle to control the target vehicle. The current health level, future attenuation and compensation control situation of the target vehicle are sent to the target vehicle to be displayed to a user. The technical scheme of the application realizes predictive diagnosis and active optimization control of hidden thermal management faults.

Description

Technical Field

[0001] This invention relates to the field of vehicle thermal management technology, and in particular to a vehicle diagnostic and control method, device, electronic device and storage medium based on a thermal management system. Background Technology

[0002] Existing automotive thermal management systems rely primarily on On-Board Diagnostics (OBD) and Diagnostic Trouble Codes (DTCs) for post-fault handling and maintenance, which is inherently lagging. Summary of the Invention

[0003] This invention provides a vehicle diagnostic and control method, device, electronic device, and storage medium based on a thermal management system, to achieve predictive diagnosis and proactive optimization control of hidden thermal management faults.

[0004] According to one aspect of the present invention, a vehicle diagnostic and control method based on a thermal management system is provided, the method comprising:

[0005] Based on the state data of multiple sample vehicles, clustering is performed on the multiple sample vehicles to obtain a first-level cluster and multiple second-level clusters corresponding to each first-level cluster, and the standard optimal energy consumption model corresponding to each second-level cluster is determined.

[0006] If a target vehicle is found to have a hidden fault according to the standard optimal energy consumption model, the current attenuation factor is calculated for the target vehicle, and the current health level of the target vehicle is determined based on the current attenuation factor.

[0007] Based on the historical attenuation factor and the current attenuation factor of the target vehicle, predict the future attenuation of the target vehicle;

[0008] Based on the current health level of the target vehicle, a thermal management compensation strategy is generated for the target vehicle to control the target vehicle, and the current health level of the target vehicle, the future degradation status, and the compensation control status are sent to the target vehicle for display to the user.

[0009] According to another aspect of the present invention, a vehicle diagnostic and control device based on a thermal management system is provided, the device comprising:

[0010] The clustering energy consumption model determination module is used to perform clustering processing on the multiple sample vehicles based on the state data of multiple sample vehicles, to obtain a first-level cluster and multiple second-level clusters corresponding to each first-level cluster, and to determine the standard optimal energy consumption model corresponding to each second-level cluster.

[0011] The health level determination module is used to calculate the current attenuation factor for the target vehicle and determine the current health level of the target vehicle based on the current attenuation factor when the target vehicle is determined to have a hidden fault according to the standard optimal energy consumption model.

[0012] The attenuation prediction module is used to predict the future attenuation of the target vehicle based on the historical attenuation factor and the current attenuation factor.

[0013] The vehicle control and status display module is used to generate a thermal management compensation strategy for the target vehicle based on the target vehicle's current health level to control the target vehicle, and to send the target vehicle's current health level, future degradation status, and compensation control status to the target vehicle for display to the user.

[0014] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program that can be executed by the at least one processor, which enables the at least one processor to perform the vehicle diagnostic and control method based on a thermal management system as described in any embodiment of the present invention.

[0018] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions, the computer instructions being configured to cause a processor to execute and implement the vehicle diagnostic and control method based on a thermal management system as described in any embodiment of the present invention.

[0019] The technical solution of this invention clusters multiple sample vehicles based on their state data to obtain a primary cluster and multiple secondary clusters corresponding to each primary cluster, and determines the standard optimal energy consumption model corresponding to each secondary cluster. If a target vehicle is found to have a hidden fault according to the standard optimal energy consumption model, the current attenuation factor is calculated for the target vehicle, and the current health level of the target vehicle is determined based on the current attenuation factor. Based on the historical and current attenuation factors of the target vehicle, future attenuation is predicted. Based on the current health level of the target vehicle, a thermal management compensation strategy is generated to control the target vehicle, and the current health level, future attenuation, and compensation control status of the target vehicle are sent to the target vehicle for display to the user. This solution employs a dynamic vehicle energy consumption cluster model based on vehicle cluster collaboration. By comparing the models, vehicles with abnormal thermal management systems are identified. The hidden physical attenuation characteristics of the internal components of these abnormal vehicles are deduced in reverse, and the on-board thermal management control loop is adaptively intervened. This solves the problem of lag in existing vehicle fault diagnosis and control maintenance, and achieves predictive diagnosis and proactive optimization control of hidden thermal management faults.

[0020] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A flowchart illustrating a vehicle diagnostic and control method based on a thermal management system, provided in Embodiment 1 of the present invention;

[0023] Figure 2 This is a schematic diagram of a vehicle diagnostic and control device based on a thermal management system provided in Embodiment 2 of the present invention;

[0024] Figure 3 This is a schematic diagram of the structure of an electronic device that implements the vehicle diagnostic and control method based on a thermal management system according to an embodiment of the present invention. Detailed Implementation

[0025] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0026] It should be noted that the terms "first," "second," etc., in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0027] Example 1

[0028] Figure 1 This is a flowchart of a vehicle diagnostic and control method based on a thermal management system provided in Embodiment 1 of the present invention. This embodiment is applicable to situations involving vehicle health diagnosis and fault prediction. The method can be executed by a vehicle diagnostic and control device based on a thermal management system, which can be implemented in hardware and / or software and can be configured in a cloud server. Figure 1 As shown, the method includes:

[0029] S110. Based on the state data of multiple sample vehicles, perform clustering processing on multiple sample vehicles to obtain a first-level cluster and multiple second-level clusters corresponding to each first-level cluster, and determine the standard optimal energy consumption model corresponding to each second-level cluster.

[0030] The sample vehicle's status data can include vehicle thermal management operating mode data, vehicle operating environment status data, and vehicle operating condition status data. Specifically, vehicle thermal management operating mode data can include, for example, cabin cooling mode, battery cooling mode, dual cooling mode, cabin heating mode, battery heating mode, and dual heating mode; vehicle operating environment status data can include, for example, outside ambient temperature, vehicle speed, the difference between the required and actual interior temperature, and the difference between the required and actual temperatures of vehicle components; vehicle operating condition status data can include, for example, charging current, mileage, traffic conditions, and battery charge.

[0031] In one optional implementation, the status data of multiple sample vehicles are clustered to obtain a primary cluster and multiple secondary clusters corresponding to each primary cluster. This may include: collecting status data of multiple sample vehicles; filtering the status data of target sample vehicles from the status data of multiple sample vehicles according to a preset filtering rule; clustering the status data of target sample vehicles according to the vehicle's thermal management working mode to obtain multiple primary clusters; and clustering the status data of target sample vehicles corresponding to each primary cluster according to the vehicle's environmental status data and operating condition status data to obtain multiple secondary clusters corresponding to each primary cluster.

[0032] The preset screening rules can be a preliminary screening rule for the sample vehicle status data. These rules can be used to initially identify obviously unhealthy vehicle status data from the sample vehicle status data. For example, vehicles that have reported DTC (Diagnostic Trouble Code) fault codes in the historical observation period, vehicles that have experienced maintenance and thermal management system alarms, and vehicles whose uploaded data packet loss rate is greater than 2%.

[0033] This embodiment can perform first-level clustering classification of the target sample vehicle's state data based on the vehicle's thermal management operating mode, directly physically isolating each pattern dataset. Based on the vehicle's operating environment and working condition data, the K-Means++ algorithm is used to perform second-level clustering classification of the vehicle data under the first-level clustering.

[0034] Based on the above optional implementation methods, according to the vehicle's environmental state data and operating condition data, the state data of the target sample vehicles corresponding to each primary cluster are clustered to obtain multiple secondary clusters corresponding to each primary cluster. This can include: determining the current primary cluster; randomly selecting a set of state data from the current primary cluster as a centroid of a secondary cluster in the current primary cluster; calculating the centroid probability for other sets of state data in the current primary cluster according to a preset centroid selection method; determining all secondary cluster centroids for the current primary cluster according to the centroid probability and a preset probability threshold; calculating the Euclidean distance between the non-centroid state data in the current primary cluster and the centroids of each secondary cluster, and assigning the non-centroid state data to the secondary cluster represented by the nearest secondary cluster centroid according to the Euclidean distance.

[0035] In this embodiment, a data platform with a clustering update cycle (e.g., 30 days) can be set up on the cloud server. This platform can continuously collect new vehicle status data and can discard the oldest historical data at each update cycle to complete the updated clustering and classification.

[0036] Specifically, in this embodiment, the current first-level cluster can be determined sequentially from the first-level clusters. Samples that have not had DTCs in the past 30 days can be selected from the current first-level clusters. Furthermore, a set of state data (ambient temperature, vehicle speed, difference between required and actual temperature, charging current, mileage, traffic conditions, and SOC status, etc.) can be randomly selected from this first-level cluster as the centroid of the first second-level cluster. ; Calculate the state data of other groups in this batch of samples to The shortest Euclidean distance, further based on this shortest Euclidean distance through Calculate the probability that other groups of state data are the centroids. Indicates the current i-th group of state data to The square of the shortest Euclidean distance, This represents all other j-group state data to The sum of the squares of the shortest Euclidean distances; further, based on the calculated probabilities and preset probability thresholds, the centroids of all secondary clusters are determined (e.g., centroids defined for high temperature, high load, high speed, low temperature, and congestion); further, through multi-dimensional spatial distance iterative allocation, the Euclidean distance from the thermal management status data of each vehicle to the centroid is calculated. ,in: Indicates the thermal management status of the remaining vehicles. The thermal management status of the centroid is represented, and the thermal management status data of each vehicle is dynamically divided into the secondary cluster represented by the nearest centroid based on Euclidean distance.

[0037] In one optional implementation, determining the standard optimal energy consumption model corresponding to each secondary cluster may include: determining the current secondary cluster; calculating the ideal thermal management energy consumption for the current secondary cluster according to a predefined ideal thermal management energy consumption model; calculating the composite residual coefficient for the current target sample vehicles under the current secondary cluster according to a predefined calculation method; wherein, the composite residual coefficient represents the difference between the actual thermal management energy consumption of the current target sample vehicles and the ideal thermal management energy consumption of the current secondary cluster within a certain continuous time period; sorting the target sample vehicles in the current secondary cluster according to the composite residual coefficient from smallest to largest, and taking the first specified proportion of target sample vehicles in the sorting result as the absolutely healthy vehicle cluster in the current secondary cluster; and using a first neural network to learn the data of the absolutely healthy vehicle cluster to obtain the standard optimal energy consumption model corresponding to the current secondary cluster.

[0038] In this embodiment, an ideal thermal management energy consumption model can be predefined for each secondary cluster, for example, ,in, This can represent the ideal thermal management energy consumption of the compressor. This can represent the ideal thermal management energy consumption of a cooling fan. This can represent the ideal thermal management energy consumption of a water pump. This can represent the ideal thermal management energy consumption of a PTC. , , , It can be a function related to ambient temperature, vehicle speed, the difference between the required temperature and the actual temperature, charging current, mileage, traffic conditions, and SOC status for thermal management.

[0039] This embodiment can also define the calculation method for the composite residual coefficient, for example, ,in, , , , These represent the actual thermal management energy consumption of the compressor, cooling fan, water pump, and PTC, respectively.

[0040] Based on the aforementioned ideal thermal management energy consumption model, the ideal thermal management energy consumption can be calculated for the current secondary cluster. Based on the aforementioned method for calculating the composite residual coefficient, the composite residual coefficient is calculated for each sample under the current secondary cluster to reflect the difference between the actual thermal management energy consumption and the ideal thermal management energy consumption of each vehicle. In this embodiment, the 10% (equivalent to a first specified proportion) of vehicles with small composite residual coefficients and good energy consumption in the current secondary cluster can be considered as the absolutely healthy vehicle cluster within that secondary cluster. Then, by using the first neural network to learn from the data of this absolutely healthy vehicle cluster, the standard optimal energy consumption model corresponding to the current secondary cluster can be obtained.

[0041] S120. If the target vehicle is found to have a hidden fault according to the standard optimal energy consumption model, calculate the current attenuation factor for the target vehicle and determine the current health level of the target vehicle based on the current attenuation factor.

[0042] In one optional implementation, determining that a target vehicle has a latent fault based on a standard optimal energy consumption model may include: determining a matching standard optimal energy consumption model for the target vehicle based on the target vehicle's status data; determining the theoretical thermal management energy consumption for the target vehicle based on the matching standard optimal energy consumption model; comparing the actual thermal management energy consumption of the target vehicle with the theoretical thermal management energy consumption; and determining that the target vehicle has a latent fault if the actual thermal management energy consumption is higher than the theoretical thermal management energy consumption by a second specified ratio.

[0043] The target vehicle can refer to the vehicle that needs to be monitored. In this embodiment, the secondary cluster to which the target vehicle belongs can be determined based on its status data. Then, the theoretical thermal management energy consumption without attenuation under the current operating conditions can be determined for the target vehicle according to the standard optimal energy consumption model corresponding to the secondary cluster. Within a certain period of time, the actual thermal management energy consumption of the target vehicle is compared with the theoretical thermal management energy consumption without attenuation. For example, if the actual thermal management energy consumption is 5% higher than the theoretical thermal management energy consumption (equivalent to a second specified proportion), it can be considered that the target vehicle has a hidden fault.

[0044] In one optional implementation, calculating the current attenuation factor for the target vehicle and determining the current health level of the target vehicle based on the current attenuation factor may include: deriving attenuation-free thermal management system parameters for the target vehicle based on a matched standard optimal energy consumption model; wherein the thermal management system parameters include initial heat transfer coefficient, flow rate, and heat transfer area; calculating the current attenuation factor for the target vehicle using a pre-established attenuation mechanism equation; wherein the attenuation mechanism equation is pre-established based on the attenuation-free thermal management system parameters, and the current attenuation factor includes a current heat transfer efficiency attenuation factor and a current flow rate attenuation factor; comparing the current attenuation factor with the threshold values ​​of each attenuation factor to determine the current health level of the target vehicle based on the comparison results; wherein the current health level includes Level 1 health, Level 2 mild attenuation, Level 3 accelerated attenuation, and Level 4 critical failure.

[0045] In this embodiment, the parameters of the thermal management system without degradation can be derived for the target vehicle based on the standard optimal energy consumption model matched with the target vehicle. (Initial heat transfer coefficient) (Flow rate), A heat exchange area; further through the attenuation mechanism equation Calculate the current heat exchange efficiency decay factor for each component of the target vehicle. and current flow attenuation factor , Indicates the specific heat capacity of the heat exchanger body. This indicates the specific heat capacity of the cooling liquid. Indicates the terminal temperature. Indicates the inlet temperature. , The logarithmic mean temperature difference represents the average heat transfer temperature difference between the fluid and the heat exchange wall. This indicates the maximum temperature difference between the hot and cold fluids at both ends of the heat exchanger. This indicates the minimum temperature difference between the hot and cold fluids at both ends of the heat exchanger.

[0046] Further diagnostics can be performed based on the current decay factor. For example:

[0047] like When this occurs, it indicates a decrease in heat transfer coefficient and an increase in thermal resistance. Component failures at this time could include (condenser / evaporator scaling, radiator blockage and aging). When the mass flow rate decreases, the component failures that may occur at this time include (refrigerant leakage, wear of the electric water pump, sticking of the three-way valve, and aging of the compressor).

[0048] like , If the components have no hidden wear and tear, they can be considered to be in Level 1 health; , This can be considered as slight deterioration of the components, a level two mild degradation; if , It can be considered that the components deteriorate at an accelerated rate, specifically at level three; if , The component can be considered to be at risk of failure, at level four critical failure. Here, 0.65, 0.85, 0.95, etc., can refer to the attenuation factor limit values ​​in this embodiment.

[0049] S130. Based on the historical and current attenuation factors of the target vehicle, predict the future attenuation of the target vehicle.

[0050] This embodiment can combine the historical attenuation factors of vehicles with hidden faults to predict the future attenuation factors of the vehicles and obtain the future attenuation of the vehicles.

[0051] In one optional implementation, predicting future attenuation of the target vehicle based on its historical and current attenuation factors may include: obtaining the historical attenuation factors of the target vehicle at different mileages; defining a mileage-based attenuation factor sequence for the target vehicle based on the historical and current attenuation factors at different mileages, and calculating the mean attenuation factor sequence and the attenuation factor slope sequence within the mileage range for the target vehicle; and inputting the attenuation factor sequence, the mean attenuation factor sequence, and the attenuation factor slope sequence into a second neural network to predict the predicted attenuation factor of the target vehicle at future mileages.

[0052] In this embodiment, if a latent fault is determined in the target vehicle, the historical attenuation factor of a certain component in the target vehicle at different mileages can be obtained from the database; further, based on the historical attenuation factor and the current attenuation factor, a mileage-based attenuation factor sequence is defined for the target vehicle. , , This represents the heat transfer efficiency degradation factor when the target vehicle travels 100 km. This represents the flow attenuation factor when the target vehicle travels 100 km.

[0053] It is also possible to calculate the average decay factor over the target vehicle's lifespan based on historical and current decay factors: , And the slope of the attenuation factor per 100km for the target vehicle: , Thus, the mean value sequence of the attenuation factor is obtained. and attenuation factor slope sequence .

[0054] Furthermore, the attenuation factor sequence, attenuation factor mean sequence, and attenuation factor slope sequence of the target vehicle can be input into the second neural network to predict the predicted attenuation factor of the target vehicle with a latent fault in the future mileage. .

[0055] S140. Based on the current health level of the target vehicle, generate a thermal management compensation strategy for the target vehicle to control the target vehicle, and send the current health level, future degradation status and compensation control status of the target vehicle to the target vehicle for display to the user.

[0056] This embodiment can select different compensation methods to control the target vehicle based on its current health level. It can also display the target vehicle's diagnostic status, prediction status, and compensation control status to the user through the vehicle terminal, allowing the user to have a more intuitive understanding of the vehicle's condition.

[0057] In one optional implementation, a thermal management compensation strategy is generated for the target vehicle to control the target vehicle based on its current health level. This may include: not generating a thermal management compensation strategy for the target vehicle when the current health level is Level 1 (healthy); generating a thermal management compensation strategy for the target vehicle to control the target vehicle according to a predefined baseline compensation model when the current health level is Level 2 (mild decay); limiting the power output of latently faulty components and calculating a first compensation power for non-latently faulty components to achieve compensation control of the target vehicle when the current health level is Level 4 (critical failure); limiting the power output of latently faulty components and calculating a second compensation power for non-latently faulty components to achieve compensation control of the target vehicle when the current health level is Level 4 (critical failure), wherein the second compensation power is greater than the first compensation power.

[0058] In this embodiment, if the target vehicle is in Level 1 health, it can be assumed that no compensation control is needed at present.

[0059] If the target vehicle exhibits a level 2 mild degradation, adaptive feedforward gain compensation can be used without altering the thermal management load requirements. Taking the fan as an example, a predefined baseline compensation model can be employed. Generate a thermal management compensation strategy for the target vehicle. It can indicate the target fan speed. It can represent the current actual rotational speed. Indicates the compensation coefficient. It can represent the difference between demand and reality.

[0060] If the target vehicle is at level three acceleration decay, power limiting and slight load transfer can be applied to the target vehicle's latent faulty components to limit the peak value of the latent faulty components; if the target vehicle is at level four critical failure, power limiting and significant load transfer can be applied to the target vehicle's latent faulty components to strictly constrain the maximum load of the faulty components.

[0061] Specifically, if level three accelerated decay and level four critical failure occur, compensation control can be achieved through the following methods:

[0062] Limit the power output of components with latent faults; calculate the compensation power required after limiting; increase the load on components with non-latent faults to ensure the overall thermal management requirements of the vehicle, for example, if Damage (compressor or water pump failure) can be addressed by increasing the load on healthy components, such as upgrading the cooling fan, auxiliary water pump, heat pump mode, and waste heat recovery. Heat exchanger failure (attenuation) can be mitigated by increasing fan speed and water pump flow rate, thereby reducing the instantaneous thermal shock of the heat exchanger.

[0063] This embodiment can also perform closed-loop temperature monitoring, and determine the temperature without lifting the power limit. Whether to expand the compensation amount of healthy components can be controlled by PI control without relaxing the limit on the hidden faulty components.

[0064] This embodiment can push maintenance notifications and emergency failure control notifications to users via HMI (Human Machine Interface) through a cloud server. VTMS (Vehicle Thermal Management System) The HMI displays the current health level of components, allowing vehicle users to understand their current health status. It also pushes notifications about the status and cause of emergency thermal management preventative controls, informing users of any abnormalities in the health of thermal management components. Furthermore, it pushes notifications about the degradation of hidden faults in components, allowing users to be aware of the component's health status in advance and enabling proactive maintenance and repair.

[0065] The technical solution of this embodiment clusters multiple sample vehicles based on their state data to obtain a primary cluster and multiple secondary clusters corresponding to each primary cluster, and determines the standard optimal energy consumption model corresponding to each secondary cluster. If the standard optimal energy consumption model determines that a target vehicle has a hidden fault, the current attenuation factor is calculated for the target vehicle, and the current health level of the target vehicle is determined based on the current attenuation factor. Based on the historical and current attenuation factors of the target vehicle, future attenuation is predicted. Based on the current health level of the target vehicle, a thermal management compensation strategy is generated to control the target vehicle, and the current health level, future attenuation, and compensation control status of the target vehicle are sent to the target vehicle for display to the user. This solution employs a dynamic vehicle energy consumption cluster model based on vehicle cluster collaboration. By comparing data, abnormal vehicles in the thermal management system are identified. The hidden physical attenuation characteristics of the internal components of the abnormal vehicles are deduced in reverse, and the on-board thermal management control loop is adaptively intervened. This solves the problem of lag in existing vehicle fault diagnosis and control maintenance, and achieves predictive diagnosis and proactive optimization control of hidden thermal management faults.

[0066] Example 2

[0067] Figure 2 This is a schematic diagram of a vehicle diagnostic and control device based on a thermal management system, provided in Embodiment 2 of the present invention. Figure 2 As shown, the device includes: a clustering energy consumption model determination module 210, a health level determination module 220, a decay prediction module 230, and a vehicle control and status display module 240. Wherein:

[0068] The clustering energy consumption model determination module 210 is used to perform clustering processing on the multiple sample vehicles based on the state data of multiple sample vehicles, to obtain a first-level cluster and multiple second-level clusters corresponding to each first-level cluster, and to determine the standard optimal energy consumption model corresponding to each second-level cluster.

[0069] The health level determination module 220 is used to calculate the current attenuation factor for the target vehicle and determine the current health level of the target vehicle based on the current attenuation factor when the target vehicle is determined to have a hidden fault according to the standard optimal energy consumption model.

[0070] The attenuation prediction module 230 is used to predict the future attenuation of the target vehicle based on the historical attenuation factor and the current attenuation factor of the target vehicle.

[0071] The vehicle control and status display module 240 is used to generate a thermal management compensation strategy for the target vehicle based on the current health level of the target vehicle in order to control the target vehicle, and to send the current health level of the target vehicle, the future attenuation status and the compensation control status to the target vehicle for display to the user.

[0072] The technical solution of this embodiment clusters multiple sample vehicles based on their state data to obtain a primary cluster and multiple secondary clusters corresponding to each primary cluster, and determines the standard optimal energy consumption model corresponding to each secondary cluster. If the standard optimal energy consumption model determines that a target vehicle has a hidden fault, the current attenuation factor is calculated for the target vehicle, and the current health level of the target vehicle is determined based on the current attenuation factor. Based on the historical and current attenuation factors of the target vehicle, future attenuation is predicted. Based on the current health level of the target vehicle, a thermal management compensation strategy is generated to control the target vehicle, and the current health level, future attenuation, and compensation control status of the target vehicle are sent to the target vehicle for display to the user. This solution employs a dynamic vehicle energy consumption cluster model based on vehicle cluster collaboration. By comparing data, abnormal vehicles in the thermal management system are identified. The hidden physical attenuation characteristics of the internal components of the abnormal vehicles are deduced in reverse, and the on-board thermal management control loop is adaptively intervened. This solves the problem of lag in existing vehicle fault diagnosis and control maintenance, and achieves predictive diagnosis and proactive optimization control of hidden thermal management faults.

[0073] Optionally, the clustering energy consumption model determination module 210 may include:

[0074] The data filtering unit is used to collect status data of multiple sample vehicles and filter out the status data of the target sample vehicle from the status data of the multiple sample vehicles according to a preset filtering rule.

[0075] The first-level clustering acquisition unit is used to cluster the status data of the target sample vehicle according to the vehicle thermal management working mode to obtain multiple first-level clusters.

[0076] The secondary clustering acquisition unit is used to cluster the state data of the target sample vehicles corresponding to each primary cluster according to the environmental state data and operating condition data of the vehicles, so as to obtain multiple secondary clusters corresponding to each primary cluster.

[0077] Optionally, the secondary clustering unit can be used to obtain the following:

[0078] Determine the current first-level cluster;

[0079] Randomly select a set of state data from the current first-level cluster as a second-level cluster centroid in the current first-level cluster;

[0080] Calculate the centroid probability for the state data of other groups in the current first-level cluster according to the preset centroid selection method;

[0081] Based on the centroid probability and the preset probability threshold, determine all secondary cluster centroids for the current first-level cluster;

[0082] Calculate the Euclidean distance between the non-centroid state data in the current first-level cluster and the centroids of each of the second-level clusters, and assign the non-centroid state data to the second-level cluster represented by the nearest second-level cluster centroid based on the Euclidean distance.

[0083] Optionally, the clustering energy consumption model determination module 210 may further include a clustering energy consumption model determination unit, used for:

[0084] Determine the current secondary cluster;

[0085] The ideal thermal management energy consumption is calculated based on the predefined ideal thermal management energy consumption model for the current second-order clustering.

[0086] The composite residual coefficient is calculated for the current target sample vehicle under the current secondary cluster according to a predefined calculation method; wherein, the composite residual coefficient represents the difference between the actual thermal management energy consumption of the current target sample vehicle and the ideal thermal management energy consumption of the current secondary cluster within a certain continuous time period;

[0087] According to the order of the composite residual coefficient from smallest to largest, the target sample vehicles in the current secondary cluster are sorted, and the first specified proportion of target sample vehicles in the sorting result are taken as the absolutely healthy vehicle cluster in the current secondary cluster.

[0088] The data of the absolutely healthy vehicle cluster is learned using the first neural network to obtain the standard optimal energy consumption model corresponding to the current secondary cluster.

[0089] Optional, the health level determination module 220 can be used for:

[0090] Based on the state data of the target vehicle, determine the matching standard optimal energy consumption model for the target vehicle;

[0091] The theoretical thermal management energy consumption is determined for the target vehicle based on the matched standard optimal energy consumption model.

[0092] Compare the actual thermal management energy consumption of the target vehicle with the theoretical thermal management energy consumption;

[0093] If the actual thermal management energy consumption is higher than the theoretical thermal management energy consumption by a second specified ratio, it is determined that the target vehicle has a latent fault.

[0094] Optionally, the health level determination module 220 can also be used for:

[0095] Based on the matching standard optimal energy consumption model, the parameters of the thermal management system without degradation are derived for the target vehicle; wherein, the thermal management system parameters include the initial heat transfer coefficient, flow rate, and heat transfer area;

[0096] The current attenuation factor is calculated for the target vehicle using a pre-established attenuation mechanism equation; wherein the attenuation mechanism equation is pre-established based on the parameters of the attenuation-free thermal management system, and the current attenuation factor includes the current heat exchange efficiency attenuation factor and the current flow rate attenuation factor.

[0097] The current attenuation factor and the threshold values ​​of each attenuation factor are compared to determine the current health level of the target vehicle based on the comparison results; wherein the current health level includes Level 1 health, Level 2 mild attenuation, Level 3 accelerated attenuation, and Level 4 critical failure.

[0098] Optional, the attenuation prediction module 230 can be used for:

[0099] Obtain the historical degradation factor of the target vehicle at different mileages;

[0100] Based on the historical attenuation factors at different mileages and the current attenuation factors, a mileage-based attenuation factor sequence is defined for the target vehicle, and a mean attenuation factor sequence and an attenuation factor slope sequence within the mileage are calculated for the target vehicle.

[0101] The attenuation factor sequence, the attenuation factor mean sequence, and the attenuation factor slope sequence are input into a second neural network to predict the predicted attenuation factor of the target vehicle in the future mileage.

[0102] Optional, the vehicle control and status display module 240 can be used for:

[0103] If the current health level is Level 1, no thermal management compensation strategy will be generated for the target vehicle.

[0104] When the current health level is Level 2 with slight degradation, a thermal management compensation strategy is generated for the target vehicle according to a predefined baseline compensation model to control the target vehicle;

[0105] When the current health level is three-level acceleration decay, the power output of the latent faulty components is limited, and a first compensation power is calculated for the non-latent faulty components to achieve compensation control for the target vehicle.

[0106] When the current health level is level four critical failure, the power output of the latently faulty component is limited, and a second compensation power is calculated for the non-latently faulty component to achieve compensatory control of the target vehicle, wherein the second compensation power is greater than the first compensation power.

[0107] The vehicle diagnostic and control device based on a thermal management system provided in this embodiment of the invention can execute the vehicle diagnostic and control method based on a thermal management system provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method.

[0108] Example 3

[0109] Figure 3 A schematic diagram of an electronic device 300 that can be used to implement embodiments of the present invention is shown. The electronic device is intended to represent various forms of digital computers or various forms of mobile devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0110] like Figure 3 As shown, the electronic device 300 includes at least one processor 301 and a memory, such as a read-only memory (ROM) 302 or a random access memory (RAM) 303, communicatively connected to the at least one processor 301. The memory stores computer programs executable by the at least one processor. The processor 301 can perform various appropriate actions and processes based on the computer program stored in the ROM 302 or loaded into the RAM 303 from storage unit 308. The RAM 303 can also store various programs and data required for the operation of the electronic device 300. The processor 301, ROM 302, and RAM 303 are interconnected via a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0111] Multiple components in electronic device 300 are connected to I / O interface 305, including: input unit 306, such as keyboard, mouse, etc.; output unit 307, such as various types of displays, speakers, etc.; storage unit 308, such as disk, optical disk, etc.; and communication unit 309, such as network card, modem, wireless transceiver, etc. Communication unit 309 allows electronic device 300 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0112] Processor 301 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 301 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, digital signal processors (DSPs), and any suitable processor, controller, microcontroller, etc. Processor 301 performs the various methods and processes described above, such as vehicle diagnostics and control methods based on a thermal management system.

[0113] In some embodiments, the vehicle diagnostic and control method based on a thermal management system can be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 308. In some embodiments, part or all of the computer program can be loaded and / or installed on electronic device 300 via ROM 302 and / or communication unit 309. When the computer program is loaded into RAM 303 and executed by processor 301, one or more steps of the vehicle diagnostic and control method based on a thermal management system described above can be performed. Alternatively, in other embodiments, processor 301 can be configured to perform the vehicle diagnostic and control method based on a thermal management system by any other suitable means (e.g., by means of firmware).

[0114] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0115] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0116] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0117] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0118] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0119] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0120] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0121] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A vehicle diagnostic and control method based on a thermal management system, characterized in that, include: Based on the state data of multiple sample vehicles, clustering is performed on the multiple sample vehicles to obtain a first-level cluster and multiple second-level clusters corresponding to each first-level cluster, and the standard optimal energy consumption model corresponding to each second-level cluster is determined. If a target vehicle is found to have a hidden fault according to the standard optimal energy consumption model, the current attenuation factor is calculated for the target vehicle, and the current health level of the target vehicle is determined based on the current attenuation factor. Based on the historical attenuation factor and the current attenuation factor of the target vehicle, predict the future attenuation of the target vehicle; Based on the current health level of the target vehicle, a thermal management compensation strategy is generated for the target vehicle to control the target vehicle, and the current health level of the target vehicle, the future degradation status, and the compensation control status are sent to the target vehicle for display to the user.

2. The method according to claim 1, characterized in that, Based on the state data of multiple sample vehicles, clustering is performed on the multiple sample vehicles to obtain a first-level cluster and multiple second-level clusters corresponding to each first-level cluster, including: Collect status data from multiple sample vehicles, and filter out the status data of the target sample vehicle from the status data of the multiple sample vehicles according to a preset filtering rule; The status data of the target sample vehicles are clustered according to the vehicle thermal management working mode to obtain multiple first-level clusters; Based on the environmental and operational status data of the vehicles, the status data of the target sample vehicles corresponding to each primary cluster are clustered to obtain multiple secondary clusters corresponding to each primary cluster.

3. The method according to claim 2, characterized in that, Based on the vehicle's environmental and operational status data, the status data of the target sample vehicles corresponding to each primary cluster are clustered to obtain multiple secondary clusters for each primary cluster, including: Determine the current first-level cluster; Randomly select a set of state data from the current first-level cluster as a second-level cluster centroid in the current first-level cluster; Calculate the centroid probability for the state data of other groups in the current first-level cluster according to the preset centroid selection method; Based on the centroid probability and the preset probability threshold, determine all secondary cluster centroids for the current first-level cluster; Calculate the Euclidean distance between the non-centroid state data in the current first-level cluster and the centroids of each of the second-level clusters, and assign the non-centroid state data to the second-level cluster represented by the nearest second-level cluster centroid based on the Euclidean distance.

4. The method according to claim 1, characterized in that, Determine the standard optimal energy consumption model corresponding to each secondary cluster, including: Determine the current secondary cluster; The ideal thermal management energy consumption is calculated based on the predefined ideal thermal management energy consumption model for the current second-order clustering. The composite residual coefficient is calculated for the current target sample vehicle under the current secondary cluster according to a predefined calculation method; wherein, the composite residual coefficient represents the difference between the actual thermal management energy consumption of the current target sample vehicle and the ideal thermal management energy consumption of the current secondary cluster within a certain continuous time period; According to the order of the composite residual coefficient from smallest to largest, the target sample vehicles in the current secondary cluster are sorted, and the first specified proportion of target sample vehicles in the sorting result are taken as the absolutely healthy vehicle cluster in the current secondary cluster. The data of the absolutely healthy vehicle cluster is learned using the first neural network to obtain the standard optimal energy consumption model corresponding to the current secondary cluster.

5. The method according to claim 1, characterized in that, The target vehicle was found to have a latent fault based on the standard optimal energy consumption model, including: Based on the state data of the target vehicle, determine the matching standard optimal energy consumption model for the target vehicle; The theoretical thermal management energy consumption is determined for the target vehicle based on the matched standard optimal energy consumption model. Compare the actual thermal management energy consumption of the target vehicle with the theoretical thermal management energy consumption; If the actual thermal management energy consumption is higher than the theoretical thermal management energy consumption by a second specified ratio, it is determined that the target vehicle has a latent fault.

6. The method according to claim 5, characterized in that, Calculating the current attenuation factor for the target vehicle and determining the current health level of the target vehicle based on the current attenuation factor, including: Based on the matching standard optimal energy consumption model, the parameters of the thermal management system without degradation are derived for the target vehicle; wherein, the thermal management system parameters include the initial heat transfer coefficient, flow rate, and heat transfer area; The current attenuation factor is calculated for the target vehicle using a pre-established attenuation mechanism equation; wherein the attenuation mechanism equation is pre-established based on the parameters of the attenuation-free thermal management system, and the current attenuation factor includes the current heat exchange efficiency attenuation factor and the current flow rate attenuation factor. The current attenuation factor and the threshold values ​​of each attenuation factor are compared to determine the current health level of the target vehicle based on the comparison results; wherein the current health level includes Level 1 health, Level 2 mild attenuation, Level 3 accelerated attenuation, and Level 4 critical failure.

7. The method according to claim 5, characterized in that, Based on the historical attenuation factor and the current attenuation factor of the target vehicle, predict the future attenuation of the target vehicle, including: Obtain the historical degradation factor of the target vehicle at different mileages; Based on the historical attenuation factors at different mileages and the current attenuation factors, a mileage-based attenuation factor sequence is defined for the target vehicle, and a mean attenuation factor sequence and an attenuation factor slope sequence within the mileage are calculated for the target vehicle. The attenuation factor sequence, the attenuation factor mean sequence, and the attenuation factor slope sequence are input into a second neural network to predict the predicted attenuation factor of the target vehicle in the future mileage.

8. The method according to claim 6, characterized in that, Based on the current health level of the target vehicle, a thermal management compensation strategy is generated for the target vehicle to control the target vehicle, including: If the current health level is Level 1, no thermal management compensation strategy will be generated for the target vehicle. When the current health level is Level 2 with slight degradation, a thermal management compensation strategy is generated for the target vehicle according to a predefined baseline compensation model to control the target vehicle; When the current health level is three-level acceleration decay, the power output of the latent faulty components is limited, and a first compensation power is calculated for the non-latent faulty components to achieve compensation control for the target vehicle. When the current health level is level four critical failure, the power output of the latently faulty component is limited, and a second compensation power is calculated for the non-latently faulty component to achieve compensatory control of the target vehicle, wherein the second compensation power is greater than the first compensation power.

9. A vehicle diagnostic and control device based on a thermal management system, characterized in that, include: The clustering energy consumption model determination module is used to perform clustering processing on the multiple sample vehicles based on the state data of multiple sample vehicles, to obtain a first-level cluster and multiple second-level clusters corresponding to each first-level cluster, and to determine the standard optimal energy consumption model corresponding to each second-level cluster. The health level determination module is used to calculate the current attenuation factor for the target vehicle and determine the current health level of the target vehicle based on the current attenuation factor when the target vehicle is determined to have a hidden fault according to the standard optimal energy consumption model. The attenuation prediction module is used to predict the future attenuation of the target vehicle based on the historical attenuation factor and the current attenuation factor. The vehicle control and status display module is used to generate a thermal management compensation strategy for the target vehicle based on the target vehicle's current health level to control the target vehicle, and to send the target vehicle's current health level, future degradation status, and compensation control status to the target vehicle for display to the user.

10. An electronic device, characterized in that, The electronic device includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform a vehicle diagnostic and control method based on a thermal management system according to any one of claims 1-8.

11. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions that cause a processor to execute and implement the vehicle diagnostic and control method based on a thermal management system as described in any one of claims 1-8.

Images