Method for identifying misaligned sensors in a vehicle

Abstract

Method (300) for identifying detuned sensors (112) in a vehicle (100), the method (300) comprising: Receiving (302) an initial measurement value from each of a plurality of sensors (112) arranged in the vehicle (100); Activating (304) one or more of a heating system and a cooling system (104) arranged in the vehicle (100); Obtain (306) a series of measurements from each of the multitude of sensors (112); Identify (308), for each of the multitude of sensors (112), a delta value from the series of measured values; Compare (310), for each of the multitude of sensors (112), the delta value with an expected delta value; Identifying (312) two or more sensors (112) from the plurality of sensors (112) that are out of tune, based on differences between the delta values ​​and the expected delta values; and Updating (314) an assignment of the two or more sensors (112) in a vehicle software (100).

Description

[0001] The description refers to the heating and cooling systems of a vehicle. More specifically, the description refers to identifying improperly installed components within the heating and cooling systems of a vehicle.

[0002] Vehicles generally have multiple heating and cooling systems that regulate the temperatures of various parts of the vehicle. These systems utilize a range of components, such as compressors, condensers, evaporators, motors, and the like. The heating and cooling systems include a network of fluid connections between these components and one or more valves that control the flow of fluid through these connections. Furthermore, the heating and cooling systems contain a control unit that manages the operation of the components and valves to heat and cool the various parts of the vehicle. The heating and cooling systems also include sensors that communicate with the control unit and monitor temperatures, pressures, and other characteristics of different parts of the vehicle.

[0003] DE 10 2021 126 870 A1 describes multimetric models of artificial intelligence (AI) / machine learning (ML) for detecting abnormal behavior of a machine / system, configured to detect anomalous behavior of systems with multiple sensors measuring correlated sensor metrics, such as coolant distribution units (CDUSs).

[0004] Improper installation of valves or sensors in heating and cooling systems often leads to malfunctions. Conventional methods for diagnosing malfunctions in heating and cooling systems are often time-consuming.

[0005] Accordingly, the object of the present invention is to provide methods that prevent improper installation of heating and cooling systems.

[0006] The problem is solved by the subject matter of the independent claims. In an exemplary embodiment, a method for identifying detuned sensors in a vehicle is provided.

[0007] According to the invention, the method comprises obtaining an initial measurement value from each of a plurality of sensors arranged in the vehicle, activating one or more of a heating system and a cooling system arranged in the vehicle, and obtaining a series of measurement values ​​from each of the plurality of sensors. The method also comprises identifying, for each of the plurality of sensors, a delta value from the series of measurement values ​​and comparing, for each of the plurality of sensors, the delta value with an expected delta value. The method further comprises identifying two or more sensors from the plurality of sensors that are detuned, based on differences between the delta values ​​and the expected delta values, and updating an assignment of the two or more sensors in the vehicle's software.

[0008] In addition to the features described here, the majority of the sensors are temperature sensors.

[0009] In addition to the one or more features described here, identifying two or more sensors from the multitude of sensors that are out of tune, based on the differences between the delta values ​​and the expected delta values, includes identifying a first sensor from the multitude of sensors that has a first delta value that is not within a first threshold range of a first expected delta value, identifying a second sensor from the multitude of sensors that has a second delta value that is not within a second threshold range of a second expected delta value, and determining that the first delta value is within the second threshold range of the second expected delta value and that the second delta value is within the first threshold range of the first expected delta value.

[0010] In addition to the features described here, the first threshold range and the second threshold range are different.

[0011] In addition to the features described here, the series of measured values ​​from each of the multitude of sensors is obtained during a predetermined period after activation of one or more of the heating or cooling systems.

[0012] In addition to the features described here, the assignment in the vehicle's software is a logical assignment between each of the multitude of sensors and a variable in the software.

[0013] In addition to the features described here, one or more of the heating and cooling systems are configured to control the temperature of a vehicle's battery pack.

[0014] In an exemplary embodiment, a method for identifying detuned sensors in a vehicle is provided. The method comprises activating one or more of a heating system and a cooling system arranged in the vehicle, receiving a set of measured values ​​from each of a plurality of sensors arranged in the vehicle, and inputting the set of measured values ​​from each of the plurality of sensors and an operating status of one or more of the heating and cooling systems into a trained machine learning model. The method also comprises receiving an indication from the trained machine learning model that two or more sensors from the plurality of sensors are detuned and updating a mapping of the two or more sensors in the vehicle's software.

[0015] In addition to the features described here, the majority of the sensors are temperature sensors.

[0016] In addition to the features described here, the trained machine learning model is trained using historical measurements from sensors arranged in a test vehicle and an operating status of heating and cooling systems corresponding to the historical measurements.

[0017] In addition to the features described here, a series of measured values ​​is obtained from each of the multitude of sensors during a predetermined period after activation of the heating or cooling system.

[0018] In addition to the features described here, the assignment in the vehicle's software is a logical assignment between each of the multitude of sensors and a variable in the software.

[0019] In addition to the features described here, the heating system and / or the cooling system are configured to control the temperature of a vehicle's battery pack.

[0020] In addition to the one or more features described herein, the method also includes receiving an identification of a check valve that has not been properly installed from the trained machine learning model, wherein the check valve is located in a fluid path of the heating or cooling system.

[0021] In one embodiment, a method according to the invention is provided for identifying an improperly installed check valve in a vehicle. The method comprises activating one or more of a heating system and a cooling system arranged in the vehicle, obtaining a series of measured values ​​from one or more sensors arranged in the vehicle, and identifying, for each of the one or more sensors, a delta value from the series of measured values. The method also comprises comparing, for each of the one or more sensors, the delta value with an expected delta value, identifying a check valve arranged in the vehicle that has not been properly installed based on the differences between the delta values ​​and the expected delta values, and generating an alarm that identifies the check valve.

[0022] In addition to the features described here, the one or more sensors include one or more pressure sensors, a temperature sensor, and a flow sensor. Furthermore, the one or more sensors are arranged in a fluid path of the heating system, the cooling system, or a combination of these systems.

[0023] In addition to the features described herein, the check valve is configured to control the flow direction in the fluid path.

[0024] In addition to the features described here, a series of measured values ​​is obtained from each of the one or multiple sensors during a predetermined period after activation of the heating or cooling system.

[0025] In addition to the features described here, the heating system and / or the cooling system are configured to control the temperature of a vehicle's battery pack.

[0026] The aforementioned features and advantages, as well as other features and advantages of the disclosure, are readily apparent from the following detailed description in conjunction with the accompanying drawings.

[0027] Further features, advantages and details are listed in the following detailed description only as examples, the detailed description referring to the drawings in which: Fig. Figure 1 is a schematic representation of a vehicle in accordance with an exemplary embodiment; Fig. Figure 2 shows a block diagram of the components of a machine learning and inference system according to an exemplary embodiment; Fig. Figure 3 is a flowchart illustrating a method for identifying detuned sensors in a vehicle in accordance with an exemplary embodiment; Fig. Figure 4 shows a block diagram of an assignment of physical sensor identifications to logical sensor identifications according to an exemplary embodiment; Fig. Figure 5 is a flowchart illustrating a method for identifying an improperly installed check valve in a vehicle according to an exemplary embodiment; Fig. 6A, Fig. 6B, Fig. 6C and Fig. Figure 6D are flowcharts illustrating a method for identifying detuned sensors in a vehicle in accordance with an exemplary embodiment; and Fig. 7A and Fig. Section 7B contains flowcharts illustrating procedures for identifying an improperly installed check valve in a vehicle according to exemplary embodiments.

[0028] The following description is merely exemplary and is not intended to limit the present disclosure, its application, or use. Various embodiments of the disclosure are described here with reference to the accompanying drawings. Alternative embodiments of the description can be developed without deviating from the scope of the claims. In the following description and in the drawings, various connections and positional relationships (for example, above, below, beside, etc.) between elements are illustrated. These connections and / or positional relationships can be direct or indirect unless otherwise specified, and the present description is not to be understood as limiting in this respect. Accordingly, a coupling of units can refer to either a direct or an indirect coupling, and a positional relationship between units can be a direct or indirect positional relationship.

[0029] To provide an overview of the aspects of the description, the embodiments of the description include methods and systems for identifying improperly installed devices in a vehicle's heating and cooling systems. In exemplary embodiments, a vehicle's processing system is configured to selectively operate the vehicle's heating and cooling systems and monitor the readings of various sensors during operation. Based on the monitored changes in the readings of various sensors, the processing system is configured to detect improperly installed devices (i.e., sensors or valves) in the heating and cooling system. In exemplary embodiments, the processing system uses various algorithms to detect misaligned sensors or improperly installed valves.In one embodiment, the processing system comprises a trained machine learning system configured to detect misaligned sensors or improperly installed valves based on the operational status of the heating and cooling system and the monitored changes in sensor readings.

[0030] In Fig. Figure 1 shows a schematic representation of a vehicle 100 according to one or more embodiments. The vehicle 100 can be an electric vehicle, a vehicle with an internal combustion engine, or a hybrid vehicle. The vehicle 100 includes a processing system 102 configured to control the operation of the heating and cooling systems 104. In exemplary embodiments, the heating and cooling systems 104 are configured to selectively heat and / or cool different parts of the vehicle 100. These different parts of the vehicle include, among others, a battery 106 of the vehicle 100 and a passenger compartment 108 of the vehicle 100. In exemplary embodiments, the processing system 102 is a general-purpose processor, a field-programmable gate array (FPGA), an application-specific integrated circuit (ASIC), or the like.

[0031] In exemplary embodiments, the vehicle 100 also includes a user interface 114 configured to receive input from a user. For example, the user interface 114 can be used to selectively activate the heating and cooling systems 104. The user interface 114 can also include a display configured to show information about the operating status of the heating and cooling systems 104.

[0032] In exemplary embodiments, the vehicle 100 comprises a plurality of sensors 112 configured to monitor one or more temperatures and pressures at various locations within the vehicle 100. For example, one of the sensors 112-1 is configured to monitor the temperature in the passenger compartment 108, one of the sensors 112 is configured to monitor the temperature of the battery 106, and another sensor 112-2 is configured to monitor the ambient temperature of the vehicle 100. In another example, one or more of the sensors 112 are configured to measure the temperatures and pressures of various components of the heating and cooling systems 104.

[0033] In exemplary embodiments, the heating and cooling systems 104 of the vehicle 100 also include a plurality of valves 110 configured to control the flow of fluid through the heating and cooling systems 104. The operation of the valves 110 is controlled by the processing system 102 to effect the operation of the heating and cooling systems 104. In exemplary embodiments, the processing system 102 is configured to receive inputs from the sensors 112, inputs from the user interface 114, and, in response, to control the operation of the heating and cooling system 104, including the valves 110.

[0034] In exemplary embodiments, the processing system 102 is configured to execute various algorithms to detect misaligned sensors or improperly installed valves. In one embodiment, the processing system 102 is configured to control the operation of the vehicle 100's heating and cooling system 104 and to monitor changes in the output of the sensors 112 during operation of the heating and cooling system. Based on the monitored changes in the output of various sensors, the processing system 102 is configured to detect improperly installed components (i.e., sensors or valves) of the heating and cooling system.In one example, the processing system 102 receives temperature readings from a first sensor 112-1, which is logically assigned to the interior of the passenger compartment 108 of the vehicle 100, and a second sensor 112-2, which is logically assigned to the exterior of the vehicle 100. However, when the processing system 102 instructs the heating and cooling system 104 to cool the interior 108 of the vehicle 100, the readings of the first sensor 112-1 remain constant, while the readings of the second sensor 112-2 decrease. Likewise, when the processing system 102 instructs the heating and cooling system 104 to heat the interior 108 of the vehicle 100, the readings of the first sensor 112-1 remain constant, while the readings of the second sensor 112-2 increase.Accordingly, the processing system 102 detects that the first sensor 112-1 and the second sensor 112-2 are detuned (that is, the mapping of the physical positions of the sensors has not been correctly reversed). In exemplary embodiments, the processing system 102 is configured to update a mapping of sensors that have been identified as detuned in the software of the vehicle 100.

[0035] In one embodiment, the processing system 102 comprises a trained machine learning system 120 configured to detect misaligned sensors or improperly installed valves based on the operational status of the heating and cooling systems 104 and the monitored changes in the output of the sensors 112. Although the trained machine learning system 120 is presented as part of the processing system 102, it is clear to those skilled in the art that the trained machine learning system 120 can be separate from the processing system 102 and can communicate with it. For example, the trained machine learning system 120 can be arranged on a diagnostic tool that can be selectively connected to the vehicle 100 to communicate with the processing system 102.

[0036] Systems for training and using a machine learning model are now being discussed with reference to Fig. 2 described in more detail. Fig. Figure 2 shows, in particular, a block diagram of the components of a machine learning system for training and inference 200 according to one or more of the embodiments described herein. The system 200 performs training 202 and inference 204. During training 202, a training machine 216 trains a model (for example, the trained model 218) to perform a task, such as identifying improperly installed devices in a vehicle's heating and cooling system. Inference 204 is the process of implementing the trained model 218 to perform the task, such as identifying improperly installed devices in a vehicle's heating and cooling system, within the context of a larger system (for example, a system 226). All or part of the components shown in Figure 216 are used to implement the trained model 218 in the context of a larger system (for example, a system 226). Fig. The system 200 shown in 2 can, for example, be represented by the entire or a subset of the processing system 102. Fig. 1 will be implemented.

[0037] The training 202 begins with training data 212, which can be structured or unstructured. According to one or more embodiments described herein, the training data 212 includes the operational status of a test vehicle's heating and cooling system and data collected by the vehicle's sensors during operation of the heating and cooling system, assuming the system is functioning correctly. The training machine 216 receives the training data 212 and a model shape 214. The model shape 214 represents an untrained base model. The model shape 214 can have preset weights and distortions that can be adjusted during training. It should be clear that the model shape 214 can be selected from many different model shapes, depending on the task to be performed.The training 202 can be supervised learning, semi-supervised learning, unsupervised learning, reinforcement learning, and / or similar methods, including combinations and / or multiples thereof. Supervised learning, for example, can be used to train a machine learning model to classify an object of interest in an image. For this purpose, the training data 212 contains labeled images, including images of the object of interest with associated labels (base truth) and other images that do not contain the object of interest with associated labels. In this example, the training module 216 takes a training image from the training data 212 as input, makes a prediction to classify the image, and compares the prediction with the known label. The training module 216 then adjusts the model's weights and / or biases based on the results of the comparison, for example, by backpropagation.The training 202 can be performed several times (referred to as "epochs") until a suitable model is trained (for example, the trained model 218).

[0038] After training, the trained model 218 can be used to make inferences 204 to perform a task, such as identifying improperly installed devices in a vehicle's heating and cooling system. The inference engine 220 applies the trained model 218 to new data 222 (for example, real, untrained data). If, for example, the trained model 218 was trained to classify images of a particular object, such as a chair, the new data 222 might be an image of a chair that was not part of the training data 212. In this way, the new data 222 represents data with which the model 218 has not yet encountered anything. The inference engine 220 makes a prediction 224 (for example, a classification of an object in an image of the new data 222) and forwards the prediction 224 to the system 226.Based on the prediction 224, the system 226 can take action, perform an operation, conduct an analysis, and / or similar actions, including combinations and / or multiples thereof. In some embodiments, the system 226 can supplement and / or modify the new data 222 based on the prediction 224.

[0039] According to one or more embodiments, the predictions 224 generated by the inference machine 220 are regularly monitored and checked to ensure that the inference machine 220 is functioning as expected. Based on this check, additional training 202 can take place, using the trained model 218 as a starting point. The additional training 202 can include all or a subset of the original training data 212 and / or new training data 212. In accordance with one or more embodiments, the training 202 includes updating the trained model 218 to account for changes in the expected input data.

[0040] In Fig. Figure 3 shows a flowchart illustrating a method 300 for identifying detuned sensors in a vehicle according to an exemplary embodiment. In exemplary embodiments, the method 300 is performed by a processing system 102, such as the one shown in Fig. The procedure 300 is carried out as shown in Figure 1. Method 300 begins in Block 302 by obtaining an initial measurement from each of a plurality of sensors arranged in the vehicle. In exemplary embodiments, the plurality of sensors includes one or more temperature sensors and / or pressure sensors. Next, in Block 304, Method 300 includes activating one or more of the heating and cooling systems arranged in the vehicle. In one embodiment, the heating and / or cooling system is configured to control the temperature of a battery pack of the vehicle.

[0041] After the heating and / or cooling system is activated, Method 300 comprises obtaining a series of measurements from each of the plurality of sensors in Block 306. In exemplary embodiments, the series of measurements is obtained from each of the plurality of sensors during a predetermined period after the activation of the heating or cooling system. In Block 308, Method 300 comprises identifying a delta value for each of the plurality of sensors from the series of measurements. In one embodiment, the delta value for the series of measurements is an average change from the initial measurement to the series of measurements during the predetermined period. In another embodiment, the delta value for the series of measurements is the largest observed change between the initial measurement and the series of measurements during the predetermined period.

[0042] In Block 310, Method 300 comprises comparing the delta value for each of the plurality of sensors with an expected delta value. In exemplary embodiments, the expected delta value for each of the plurality of sensors is an expected change in the sensor's measured value based on the operating mode of the heating and cooling system. In one embodiment, the expected delta values ​​for each of the plurality of sensors are a constant value specified by the vehicle manufacturer. In Block 312, Method 300 comprises identifying two or more sensors from the plurality of sensors that are out of tune based on differences between the delta values ​​and the expected delta values.

[0043] In one embodiment, identifying two or more sensors from the plurality of sensors that are out of tune, based on the differences between the delta values ​​and the expected delta values, comprises identifying a first sensor from the plurality of sensors that has a first delta value that is not within a first threshold range of a first expected delta value, and identifying a second sensor from the plurality of sensors that has a second delta value that is not within a second threshold range of a second expected delta value. Identifying the out-of-tune sensors also comprises determining that the first delta value is within the second threshold range of the second expected delta value and that the second delta value is within the first threshold range of the first expected delta value.In exemplary embodiments, the first threshold range and the second threshold range are different.

[0044] In block 314, method 300 comprises updating an assignment of the two or more sensors in the vehicle's software. In one embodiment, the assignment in the vehicle's software is a logical assignment between each of the plurality of sensors and a variable in the software.

[0045] In Fig. Figure 4 shows a block diagram of a mapping 400 of physical sensor identifications to logical sensor identifications according to an exemplary embodiment. As shown, the mapping 400 comprises a correspondence between a physical sensor identification 402 and a logical sensor identification 404. In one embodiment, the physical sensor identification 402 is associated with a physical connector used to connect a sensor to a vehicle. In another embodiment, the logical sensor identification 404 is a software variable associated with a sensor connected to the vehicle. In exemplary embodiments, updating the mapping 400 may involve replacing 406 of the logical sensor identification 404 associated with the physical sensor identification 402.

[0046] In Fig. Figure 5 shows a flowchart illustrating a method 500 for identifying an improperly installed check valve in a vehicle according to an exemplary embodiment. In exemplary embodiments, the method 500 is performed by a processing system 102, such as the one shown in Figure 5. Fig. The process is carried out as shown in Figure 1. In Block 502, Method 500 comprises activating one or more heating and cooling systems located in the vehicle. Next, in Block 504, Method 500 comprises obtaining a series of readings from one or more sensors located in the vehicle. In exemplary embodiments, the series of readings is obtained from each of the one or more sensors during a predetermined period after the activation of the one or more heating and cooling systems. In one embodiment, the heating and / or cooling systems are configured to control the temperature of a battery pack of the vehicle. In one embodiment, the one or more sensors comprise one or more pressure sensors, a temperature sensor, and a flow sensor.In one embodiment, one or a plurality of sensors are arranged in a fluid path of the heating system and / or the cooling system.

[0047] Next, in block 506, method 500 comprises determining a delta value from the series of measurements for each of the sensors or sensors. In one embodiment, the delta value for the series of measurements of a sensor is the total change in the sensor's measurements in the series of measurements (that is, the largest measurement of the sensor in the series of measurements minus the smallest measurement of the sensor in the series of measurements). In another embodiment, the delta value for the series of measurements is the largest observed change from an initial measurement of the sensor to the measurements in the series of measurements. In block 508, method 500 comprises comparing the delta value for each of the sensors with an expected delta value.In exemplary embodiments, the expected delta value for each of the plurality of sensors is an expected change in the sensor's measured value based on the operating mode of the heating and cooling system.

[0048] Next, in Block 510, Method 500 includes identifying a vehicle-mounted check valve that has not been properly installed based on differences between the delta values ​​and the expected delta values. In one example, a check valve is identified as improperly installed if it is determined that the difference between a delta value of one or more sensors deviates from the corresponding expected delta values ​​by more than a threshold. In exemplary embodiments, the check valve is configured to control the flow direction in the fluid path. Once a vehicle-mounted check valve has been identified as improperly installed, Method 500 proceeds to Block 512 and includes generating an alarm that identifies the check valve.

[0049] In the Fig. 6A, Fig. 6B, Fig. 6C and Fig. Figure 6D shows a flowchart illustrating a method 600 for identifying detuned sensors in a vehicle in accordance with an exemplary embodiment. In exemplary embodiments, the method 600 is performed by a processing system 102, such as the one shown in Fig. The procedure shown in Figure 1 is carried out. In block 602, procedure 600 includes receiving a command to start a diagnostic process to identify misaligned sensors. Next, in decision block 604, procedure 600 determines whether the vehicle is in a service mode. Based on the determination that the vehicle is not in a service mode, procedure 600 proceeds to block 620, and the diagnostic process is not performed. In decision block 608, procedure 600 determines whether a battery cooling process is being performed. If the battery cooling process is not being performed, procedure 600 proceeds to block 620, and the diagnostic process is not performed. If the battery cooling process is being performed, procedure 600 proceeds to block 612 and activates a diagnostic process to detect misaligned sensors in a battery cooling system.

[0050] In decision block 606, procedure 600 determines whether the vehicle's ambient temperature is within a threshold range. If the vehicle's ambient temperature is within the threshold, procedure 600 proceeds to block 614 and activates a diagnostic process to detect malfunctioning sensors by heating the interior. If the vehicle's ambient temperature is not within the threshold range, procedure 600 proceeds to block 616 and activates a diagnostic process to detect malfunctioning sensors by cooling the cabin.

[0051] In block 622, procedure 600 includes opening a radiator expansion valve and an evaporator expansion valve, and closing an external condenser flow valve and a condenser heater flow valve. In the next step, in decision block 624, procedure 600 determines whether a reading from the condenser heater temperature sensor is increasing, a temperature sensor from the front evaporator and the external condenser remains approximately constant, and a coolant radiator temperature sensor is within a threshold range. If so, the temperature sensors are functioning as expected, and procedure 600 proceeds to block 628. Otherwise, the temperature sensors are not functioning as expected, and procedure 600 proceeds to decision block 630.

[0052] In decision block 630, procedure 600 determines whether the condenser heater temperature sensor is within a threshold range of the coolant radiator temperature sensor and whether the coolant radiator temperature sensor reading is increasing. If so, procedure 600 proceeds to block 632 and determines that the condenser heater temperature sensor and the coolant radiator temperature sensor do not match. Otherwise, procedure 600 proceeds to decision block 634 and determines whether the condenser heater temperature sensor reading remains approximately constant and the front evaporator temperature reading is increasing. If so, procedure 600 proceeds to block 636 and determines that the condenser heater temperature sensor and the front evaporator temperature sensor do not match.

[0053] In block 638, procedure 600 includes closing a condenser heater flow valve and a radiator expansion valve, and opening an evaporator expansion valve and an external condenser flow valve. In the next step, in decision block 640, procedure 600 determines whether the readings from the front evaporator temperature sensor decrease and whether the readings from the radiator outside temperature sensor and the heater condenser temperature sensors remain approximately constant. If so, the temperature sensors are functioning as expected, and procedure 600 proceeds to block 644. Otherwise, the temperature sensors are not functioning as expected, and procedure 600 proceeds to decision block 646.

[0054] In decision block 646, procedure 600 determines whether the readings of the temperature sensor at the radiator outlet decrease and the readings of the temperature sensor at the front evaporator remain approximately constant. If so, procedure 600 proceeds to block 648 and determines that the temperature sensor at the radiator outlet and the temperature sensor at the front evaporator do not match. Otherwise, procedure 600 proceeds to decision block 650 and determines whether the readings of the temperature sensor at the heater condenser decrease and the readings of the temperature sensor at the front evaporator remain approximately constant. If so, procedure 600 proceeds to block 652 and identifies the temperature sensor at the heater condenser and the temperature sensor at the front evaporator as mismatched or not matching, respectively.

[0055] In block 654, procedure 600 includes closing an evaporator expansion valve and a condenser heater flow valve, and opening an external condenser flow valve and a radiator expansion valve. Next, in decision block 656, procedure 600 includes determining whether the reading of a refrigerant cooler outside temperature sensor is within a threshold range of the reading of the refrigerant temperature sensor, and whether the readings of the front evaporator temperature sensor and the heater condenser temperature sensors remain approximately constant. If so, the temperature sensors are functioning as expected, and procedure 600 proceeds to block 658. Otherwise, the temperature sensors are not functioning as expected, and procedure 600 proceeds to decision block 662.

[0056] In decision block 662, procedure 600 determines whether the reading of the front evaporator temperature sensor is within a threshold range of the reading of the coolant radiator outlet temperature sensor and whether the coolant radiator outlet temperature sensor remains approximately constant. If so, procedure 600 proceeds to block 664 and determines that the coolant radiator outlet temperature sensor and the front evaporator temperature sensor do not match. Otherwise, procedure 600 proceeds to decision block 666 and determines whether the reading of the heater condenser sensor is within a threshold range of the reading of the coolant radiator outlet sensor and whether the reading of the coolant radiator outlet sensor remains approximately constant.If this is the case, procedure 600 proceeds to block 668 and identifies the coolant cooler outlet temperature sensor and the heater condenser temperature sensor as mismatched.

[0057] In Fig. Figure 7A shows a flowchart illustrating a method 700 for identifying an improperly installed check valve in a vehicle according to an exemplary embodiment. In exemplary embodiments, the method 700 is performed by a processing system 102, such as the one shown in Figure 7A. Fig. The procedure shown in Figure 1 was performed. In Block 702, Procedure 700 includes activating a diagnostic process for the cabin cooling check valve. Next, in Block 704, Procedure 700 includes setting an evaporator expansion valve and a condenser flow valve to more than ten percent opening and setting a heater flow valve and a radiator expansion valve to less than ten percent opening.Next, in decision block 706, procedure 700 includes determining whether the difference between the readings of a compressor ambient temperature sensor and an expansion valve inlet temperature sensor is greater than a threshold, whether the difference between the readings of a compressor ambient temperature sensor and an external condenser ambient temperature sensor is greater than a threshold, and whether the difference between the readings of a compressor mass flow sensor and an external condenser sensor is greater than a threshold. If all these conditions are met, procedure 700 proceeds to block 708, and an external condenser check valve misalignment is determined. Otherwise, the procedure proceeds to block 710, and an external condenser check valve misalignment is not detected.

[0058] In Fig. Figure 7B shows a flowchart illustrating a method 720 for identifying an improperly installed check valve in a vehicle according to an exemplary embodiment. In exemplary embodiments, the method 720 is performed by a processing system 102, such as the one shown in Figure 7B. Fig.The procedure shown in Figure 1 is performed. In Block 722, Procedure 720 involves activating a diagnostic process for the cabin heater check valve. Next, in Block 724, an evaporator expansion valve and a condenser flow valve are set to be less than 10 percent open, and a heater flow valve and a radiator expansion valve are set to be more than 10 percent open.Next, as shown in Decision Block 726, Procedure 720 includes determining whether there is a difference between the readings of a compressor ambient temperature sensor and an expansion valve inlet temperature sensor greater than a threshold, whether there is a difference between the readings of a compressor ambient temperature sensor and a cabin heater condenser ambient temperature sensor greater than a threshold, and whether there is a difference between the readings of a compressor mass flow sensor and a cabin heater condenser sensor greater than a threshold. If all of these conditions are met, Procedure 720 proceeds to Block 728, and misalignment of the cabin heater condenser check valve is determined. Otherwise, the procedure proceeds to Block 730, and misalignment of the cabin heater condenser check valve is not detected.

Claims

[1] Method (300) for identifying detuned sensors (112) in a vehicle (100), the method (300) comprising: Receiving (302) an initial measurement value from each of a plurality of sensors (112) arranged in the vehicle (100); Activating (304) one or more of a heating system and a cooling system (104) arranged in the vehicle (100); Obtain (306) a series of measurements from each of the multitude of sensors (112); Identify (308), for each of the multitude of sensors (112), a delta value from the series of measured values; Compare (310), for each of the multitude of sensors (112), the delta value with an expected delta value; Identifying (312) two or more sensors (112) from the plurality of sensors (112) that are out of tune, based on differences between the delta values ​​and the expected delta values; and Updating (314) an assignment of the two or more sensors (112) in a vehicle software (100). [2] Method (300) according to claim 1, wherein the plurality of sensors (112) are temperature sensors. [3] Method (300) according to claim 1, comprising the identification (312) of two or more sensors (112) from the plurality of sensors (112) that are out of tune, which is based on the differences between the delta values ​​and the expected delta values: Identifying a first sensor (112) from the plurality of sensors (112) that has a first delta value that is not within a first threshold range of a first expected delta value; Identifying a second sensor (112) of the plurality of sensors (112) that exhibits a second delta value that is not within a second threshold range of a second expected delta value; and Determine that the first delta value lies within the second threshold range of the second expected delta value and that the second delta value lies within the first threshold range of the first expected delta value. [4] Method (300) according to claim 3, wherein the first threshold range and the second threshold range are different. [5] Method (300) according to claim 1, wherein the series of measured values ​​is obtained from each of the plurality of sensors (112) during a predetermined period after activation of one or more of the heating system or cooling system (104). [6] Method (300) according to claim 1, wherein the mapping in the software of the vehicle is a logical mapping between each of the plurality of sensors (112) and a variable in the software. [7] Method (300) according to claim 1, wherein one or more of the heating system and the cooling system (104) are configured to control the temperature of a battery pack of the vehicle (100). [8] Method (300) for identifying detuned sensors (112) in a vehicle (100), the method (300) comprising: Activating (304) one or more of a heating system and a cooling system (104) arranged in the vehicle (100); Receive (306) a series of measured values ​​from each of a plurality of sensors (112) arranged in the vehicle (100); Inputting the series of measured values ​​from each of the multiple sensors (112) and an operating status of one or more of the heating system and cooling system (104) into a trained machine learning model; Receiving an indication from the trained machine learning model that two or more sensors (112) out of the plurality of sensors (112) are detuned; and updating (314) an assignment of the two or more sensors (112) in a software of the vehicle (100). [9] Method (300) according to claim 8, wherein the plurality of sensors (112) are temperature sensors. [10] Method (500) for identifying an improperly installed check valve in a vehicle (100), the method (500) comprising: Activating (502) one or more of a heating system and a cooling system (104) arranged in the vehicle (100); Receive (504) a series of measured values ​​from one or more sensors (112) arranged in the vehicle (100); Identify (506), for each of the one or more sensors (112), a delta value from the series of measured values; Compare (508), for each of the one or more sensors (112), the delta value with an expected delta value; Identifying (510) a check valve located in the vehicle (100) that has not been properly installed, based on the differences between the delta values ​​and the expected delta values; and Generating (512) an alarm that identifies the check valve.

Images