CN116945843A

CN116945843A - Enhanced vehicle operation

Info

Publication number: CN116945843A
Application number: CN202210412346.7A
Authority: CN
Inventors: S·赛义德萨莱希; V·克里夫佐夫; W·S·约翰斯顿; T·A·蒙哥马利; 凯文·迈克尔·斯温斯科斯基; A·杜博维茨基; M·贾汉巴尼法德; J·金
Original assignee: Ford Global Technologies LLC
Current assignee: Ford Global Technologies LLC
Priority date: 2022-04-19
Filing date: 2022-04-19
Publication date: 2023-10-27

Abstract

The present disclosure provides for "enhanced vehicle operation". A computer comprising a processor and a memory, the memory storing instructions executable by the processor to: collecting (a) ambient weather data, (b) vehicle speed data including at least one of a vehicle speed or an engine speed, and (c) operational data of a climate control subsystem of the vehicle; inputting the collected data into a regression program trained to output predicted refrigerant pressure of the climate control subsystem, the regression program trained with previously determined ambient weather data, previous vehicle speed or previous engine speed data, and previous operating data of the climate control subsystem; determining the actual pressure of the refrigerant in the climate control subsystem; and actuating a component upon determining that the difference between the predicted pressure and the actual pressure falls below a threshold.

Description

Enhanced vehicle operation

Technical Field

The present disclosure relates to climate control systems in vehicles.

Background

The climate control subsystem provides heating and/or cooling to the cabin of the vehicle. The climate control subsystem is operable to cool the cabin by delivering a refrigerant through the thermal cycle to absorb heat from the cabin and exhausting heat from the vehicle in conjunction with the fan, blower and duct to move air between the cabin and the climate control subsystem. The climate control subsystem may operate as a radiator for a vehicle engine to heat the cabin by transferring waste heat from the engine into the cabin.

Disclosure of Invention

A system comprising a computer comprising a processor and a memory, the memory storing instructions executable by the processor to: collecting (a) ambient weather data, (b) vehicle speed data including at least one of a vehicle speed or an engine speed, and (c) operational data of a climate control subsystem of the vehicle; inputting the collected data into a regression program trained to output predicted refrigerant pressure of the climate control subsystem, the regression program trained with previously determined ambient weather data, previous vehicle speed or previous engine speed data, and previous operating data of the climate control subsystem; determining the actual pressure of the refrigerant in the climate control subsystem; and actuating a component upon determining that the difference between the predicted pressure and the actual pressure falls below a threshold.

The instructions may further include instructions to: the regression routine is retrained using the collected data and the previously determined data by applying a first weight value to the collected data and a second weight value to the previously determined data, the first weight value being greater than the second weight value.

The instructions may further include instructions to: the predicted pressure is output based on a plurality of previously predicted pressure differentials of the refrigerant of the climate control subsystem.

The instructions may further include instructions to: each of the plurality of previously predicted differential pressures is determined as a respective average of the predicted differential pressures during previous respective trips, each trip being a period of time between activation of the vehicle and deactivation of the vehicle.

The threshold may be based on a standard deviation of the plurality of previously predicted differential pressures from an average of the previously predicted differential pressures.

The threshold may also be based on a false positive rate of the predicted pressure indicative of the refrigerant leak in the climate control subsystem.

The instructions may further include instructions to: the difference between the predicted pressure and the actual pressure is determined based on a predicted false positive rate of the predicted pressure indicative of a leak in the climate control subsystem.

The operational data of the climate control subsystem may include a blower speed and an evaporation temperature of the refrigerant.

The instructions may further include instructions to: a baseline pressure differential of the refrigerant of the climate control subsystem is determined based on the previous operating data of the climate control subsystem.

The instructions may further include instructions to: the reference pressure difference of the refrigerant is updated based on an average pressure difference between the predicted pressure of the refrigerant and the actual pressure of the refrigerant during a period from activation of the vehicle to deactivation of the vehicle.

The instructions may further include instructions to: the component is actuated when the difference between the predicted pressure and the actual pressure exceeds the threshold for a run time exceeding a time threshold.

The regression routine may be a multi-element adaptive regression spline.

The instructions to actuate the components may include instructions to deactivate a compressor of the climate control subsystem.

A method, comprising: collecting (a) ambient weather data, (b) vehicle speed data including at least one of a vehicle speed or an engine speed, and (c) operational data of a climate control subsystem of the vehicle; inputting the collected data into a regression program trained to output predicted refrigerant pressure of the climate control subsystem, the regression program trained with previously determined ambient weather data, previous vehicle speed or previous engine speed data, and previous operating data of the climate control subsystem; determining the actual pressure of the refrigerant in the climate control subsystem; and actuating a component upon determining that the difference between the predicted pressure and the actual pressure falls below a threshold.

The method may further include retraining the regression program using the collected data and the previously determined data by applying a first weight value to the collected data and a second weight value to the previously determined data, the first weight value being greater than the second weight value.

The method may further include outputting the predicted pressure based on a plurality of previously predicted differential pressures of the refrigerant of the climate control subsystem.

The method may further include determining each of the plurality of previously predicted differential pressures as a respective average of the predicted differential pressures during previous respective trips, each trip being a period of time between activation of the vehicle and deactivation of the vehicle.

The method may also include determining the difference between the predicted pressure and the actual pressure based on a predicted false positive rate of the predicted pressure indicative of a leak in the climate control subsystem.

The method may further include determining a baseline pressure differential of the refrigerant of the climate control subsystem based on the previous operating data of the climate control subsystem.

The method may further include updating the reference pressure differential of the refrigerant based on an average pressure differential between the predicted pressure of the refrigerant and the actual pressure of the refrigerant during a period from start-up of the vehicle to shutdown of the vehicle.

The method may further include actuating the component when the difference between the predicted pressure and the actual pressure exceeds the threshold for a run time exceeding a time threshold.

The method may further include disabling a compressor of the climate control subsystem upon determining that the difference between the predicted pressure and the actual pressure falls below the threshold.

A computing device programmed to perform any of the above method steps is also disclosed. A vehicle including a computing device is also disclosed. Also disclosed is a computer program product comprising a computer readable medium storing instructions executable by a computer processor to perform any of the above-described method steps.

Leaks in the climate control subsystem may release refrigerant, thereby reducing the amount of refrigerant available to cool the passenger compartment of the vehicle. Because the refrigerant is compressed to a liquid state and then evaporated to a vapor state during operation of the climate control subsystem, it may be difficult to determine the amount of refrigerant. That is, directly measuring the actual volume of refrigerant can be difficult because the refrigerant has different densities in the liquid state, the vapor state, and the mixed state where both liquid and vapor refrigerant are present. Furthermore, actuation of certain vehicle components may affect the condition of the refrigerant. For example, the operation of a compressor of a climate control subsystem may be affected by inputs from an internal combustion engine and ambient weather conditions. For example, an increase in the speed of the internal combustion engine may increase the speed of the compressor, thereby compressing the refrigerant to a pressure higher than the default speed of the compressor.

As explained herein, using vehicle speed data, ambient weather data, and operational data of vehicle components may provide a more accurate prediction of the volume of refrigerant in the climate control subsystem than using pressure sensors alone to determine the volume of refrigerant. The vehicle computer may collect vehicle speed data, ambient weather data, and operation data without additional sensors, and the vehicle computer may predict the volume of refrigerant without additional dedicated sensors, thereby reducing the production cost of the vehicle. Thus, the vehicle computer may be programmed to detect refrigerant leaks in the vehicle climate control subsystem using data that is otherwise available to the vehicle computer.

Drawings

FIG. 1 is a diagram of an exemplary system for detecting leaks in a climate control subsystem.

FIG. 2 is a diagram of a climate control subsystem.

FIG. 3 is a graph of pressure data for the climate control subsystem.

FIG. 4 is a diagram of an exemplary process for detecting leaks in a climate control subsystem.

Detailed Description

FIG. 1 illustrates an exemplary system 100 for detecting leaks in a climate control subsystem of a vehicle 105. The computer 110 in the vehicle 105 is programmed to receive the collected data from the one or more sensors 115. For example, the data of the vehicle 105 may include a position of the vehicle 105, data about a natural environment around the vehicle, data about an object external to the vehicle (such as another vehicle), and the like. The location of the vehicle 105 is typically provided in a conventional form, such as geographic coordinates (such as latitude and longitude coordinates) obtained via a navigation system using a Global Positioning System (GPS). Additional examples of data may include measurements of systems and components of the vehicle 105, such as the speed of the vehicle 105, the trajectory of the vehicle 105, and so forth.

The computer 110 is typically programmed to communicate over a network of vehicles 105, including, for example, a communication bus (such as a CAN bus, LIN bus, etc.) and/or other wired and/or wireless technologies (e.g., ethernet, WIFI, etc.) of a conventional vehicle 105. The computer 110 may transmit and/or receive messages to and/or from various devices (e.g., controllers, actuators, sensors, etc., including the sensor 115) in the vehicle 105 via a network, bus, and/or other wired or wireless mechanism (e.g., a wired or wireless local area network in the vehicle 105). Alternatively or additionally, where the computer 110 actually includes multiple devices, a vehicle network may be used for communication between the devices represented in this disclosure as the computer 110. For example, computer 110 may be a general purpose computer having a processor and memory as described above, and/or may include special purpose electronic circuitry including an ASIC fabricated for specific operations, such as an ASIC for processing sensor data and/or transmitting sensor data. In another example, computer 110 may include an FPGA (field programmable gate array), which is an integrated circuit fabricated to be configurable by a user. Typically, digital and mixed signal systems such as FPGAs and ASICs are described using hardware description languages such as VHDL (very high speed integrated circuit hardware description language) in electronic design automation. For example, ASICs are manufactured based on VHDL programming provided prior to manufacture, while logic components within FPGAs may be configured based on VHDL programming stored, for example, in a memory electrically connected to FPGA circuitry. In some examples, a combination of processors, ASICs, and/or FPGA circuitry may be included in computer 110.

In addition, the computer 110 may be programmed to communicate with a network 125, which, as will be described below, may include various wired and/or wireless networking technologies, such as cellular,Low power consumption (BLE), wired and/or wireless packet networks, etc.

The memory may be of any type, for example, a hard disk drive, a solid state drive, a server, or any volatile or non-volatile medium. The memory may store acquired data sent from the sensor 115. The memory may be a separate device from the computer 110, and the computer 110 may retrieve the information stored by the memory via a network in the vehicle 105 (e.g., through a CAN bus, a wireless network, etc.). Alternatively or additionally, the memory may be part of the computer 110, for example as memory of the computer 110.

The sensor 115 may comprise a variety of devices. For example, various controllers in the vehicle 105 may act as sensors 115 to provide data, such as data related to vehicle speed, acceleration, position, subsystem and/or component status, etc., via a network or bus of the vehicle 105. Further, the other sensors 115 may include cameras, motion detectors, etc., i.e., sensors 115 for providing data to assess the position of components, assess the grade of a road, etc. The sensor 115 may also include, but is not limited to, short range radar, long range radar, lidar, and/or an ultrasonic transducer.

The collected data may include a variety of data collected in the vehicle 105. Examples of the data collected are provided above, and in addition, the data is typically collected using one or more sensors 115, and may additionally include data calculated therefrom in the computer 110 and/or at the server 130. In general, the data collected may include any data that may be collected by the sensor 115 and/or calculated from such data.

The vehicle 105 may include a plurality of vehicle components 120. In this context, each vehicle component 120 includes one or more hardware components adapted to perform mechanical functions or operations, such as moving the vehicle 105, slowing or stopping the vehicle 105, steering the vehicle 105, and the like. Non-limiting examples of components 120 include: propulsion components (including, for example, an internal combustion engine and/or an electric motor, etc.), transmission components, steering components (which may include, for example, one or more of a steering wheel, a steering rack, etc.), braking components, park assist components, adaptive cruise control components, adaptive steering components, movable seating, and the like. The component 120 may include a computing device, such as an Electronic Control Unit (ECU) or the like and/or a computing device such as that described above with respect to the computer 110, and which also communicates via the vehicle 105 network.

The system 100 may also include a network 125 connected to the server 130. The computer 110 may also be programmed to communicate with one or more remote sites, such as a server 130, via a network 125In communication, the remote site may include a processor and memory. Network 125 represents one or more mechanisms by which vehicle computer 110 may communicate with remote server 130. Thus, the network 125 may be one or more of a variety of wired or wireless communication mechanisms, including any desired combination of wired (e.g., cable and fiber optic) and/or wireless (e.g., cellular, wireless, satellite, microwave, and radio frequency) communication mechanisms, as well as any desired network topology (or topologies when multiple communication mechanisms are utilized). Exemplary communication networks include wireless communication networks (e.g., usingLow power consumption (BLE), IEEE 802.11, vehicle-to-vehicle (V2V) such as Dedicated Short Range Communication (DSRC), etc.), local Area Networks (LANs), and/or Wide Area Networks (WANs) including the internet.

The vehicle 105 includes a climate control subsystem 135. The climate control subsystem 135 controls the air temperature in the passenger compartment of the vehicle 105. As described below, the climate control subsystem 135 uses the refrigerant to remove heat from the passenger compartment and expel the heat to the natural environment outside of the vehicle 105.

Fig. 2 is a diagram of an exemplary climate control subsystem 135. As described above, the climate control subsystem 135 adjusts the temperature of the air in the vehicle 105. The computer 110 may actuate the climate control subsystem 135 to provide a specified temperature of the cabin of the vehicle 105. The climate control subsystem 135 uses the refrigerant to control the temperature in the vehicle 105. The refrigerant is a chemical substance that can absorb and release heat in a controlled manner to control the temperature of the air in the cabin. For example, the refrigerant may be chlorodifluoromethane (R-22), tetrafluoroethane (R-134), a combination of other chemicals (such as R-410A), and the like. Because the refrigerant absorbs and releases heat, refrigerant leakage may reduce the amount of heat that can be absorbed and released, thereby reducing the effectiveness of the climate control subsystem 135.

The climate control subsystem 135 includes a compressor 200. The compressor 200 compresses the refrigerant to a designated pressure. Compressing the refrigerant reduces the volume of the refrigerant and increases the temperature of the refrigerant. The compressor 200 may be, for example, a screw compressor, a scroll compressor, a centrifugal compressor, or the like. Refrigerant enters the compressor 200 in the vapor phase. During operation of the climate control subsystem 135, a lubricant, such as oil, may be added to the refrigerant to lubricate the compressor 200. Thus, when refrigerant leaks from the climate control subsystem 135, the compressor 200 may lack the necessary lubrication and may be damaged during operation.

The compressor 200 provides compressed refrigerant to a condenser 205. The condenser 205 allows the refrigerant to dissipate heat to the ambient air outside the vehicle 105, thereby reducing the temperature of the refrigerant. That is, the temperature of the compressed refrigerant may be higher than the ambient air temperature outside of the vehicle 105, and thus heat may be transferred from the refrigerant to the ambient air outside of the vehicle 105. Condenser 205 includes tubes through which compressed refrigerant moves. The cooling fan 210 may blow ambient air outside the vehicle 105 through the tubes, thereby reducing the temperature of the tubes and refrigerant by convective cooling. The air heated by the tube may be exhausted from the vehicle 105. As the refrigerant cools in condenser 205, the refrigerant condenses into a liquid phase (i.e., a liquid state).

The condenser 205 provides cooled refrigerant to the expansion valve 215. The expansion valve 215 reduces the pressure of the liquid refrigerant, thereby causing the temperature of the refrigerant to drop after exiting the expansion valve 215. The expansion valve 215 provides the cooled refrigerant to the condenser 220. The expansion valve 215 restricts the flow of refrigerant into the evaporator 220, thereby reducing the pressure of the refrigerant. The evaporation of the refrigerant reduces the temperature of the evaporator 220. That is, as the pressure of the refrigerant decreases, the evaporation temperature of the refrigerant decreases and the refrigerant absorbs energy to evaporate to the gas phase, and the temperature of the evaporator 220 decreases. Thus, the temperature of the refrigerant in the evaporator 220 is lower than the temperature of the ambient air in the vehicle 105. The evaporator 220 includes tubes through which cooled refrigerant moves. The blower 225 blows air inside or outside the vehicle 105 through the cooling pipe, thereby cooling the air. The cooled air is provided to the cabin of the vehicle 105, thereby cooling the air in the vehicle 105. The heated refrigerant moves to the compressor 200 to be compressed.

The computer 110 may detect refrigerant leaks in the climate control subsystem 135. A "leak" is any damaged portion of the climate control subsystem 135 through which refrigerant exits the climate control subsystem 135. When refrigerant leaks from the climate control subsystem 135, the climate control subsystem 135 is less efficient at cooling the cabin of the vehicle 105 than when the climate control subsystem 135 is not leaking. Early detection of leaks may prevent excessive release of refrigerant into the natural environment, prevent damage to the compressor 200, and/or reduce maintenance costs of the climate control subsystem 135.

The computer 110 may collect operational data of the climate control subsystem 135. In this context, "operational data" is data regarding one or more portions of the climate control subsystem 135. The operation data may include, for example, a pressure of the refrigerant leaving the compressor 200, a rotational speed of the blower 225, a rotational speed of the cooling fan 210, an evaporation temperature of the refrigerant, an air temperature outside the vehicle 105, a specified target temperature, and the like.

The computer 110 may collect vehicle speed data. The vehicle speed data may include the wheel speed of the vehicle 105 measured by the speedometer and the engine speed of the propulsion device of the vehicle 105. The speed data may be used to detect leaks. Rotation of the propulsion device may affect the performance of the compressor 200 and, thus, the engine speed may affect the operation of the compressor 200. Vehicle speed may affect the airflow under the hood of the vehicle 105, thereby affecting heat transfer from the condenser 205 to the ambient air outside the vehicle 105.

The computer 110 may collect ambient weather data. In this context, "ambient weather data" is natural ambient weather data for the geographic area surrounding the vehicle 105. Ambient weather data may include, for example, air temperature, precipitation level, precipitation type, insolation (i.e., amount of insolation), and the like. Accordingly, the computer 110 may use the ambient weather data to identify leaks in the climate control subsystem 135, as described below.

Computer 110 may generate a regression routine based on the collected data. A "regression routine" is an algorithm that relates changes in one or more variables to changes in predicted response variables. The "response variable" is a designated output of the regression routine, such as the pressure of the climate control subsystem 135. That is, the regression program determines the dependencies between two or more variables and their interactive effects on the predicted response variables. The computer 110 may generate a regression routine to predict the pressure of the refrigerant based on one or more input variables. The transformed argument of the Principal Component (PC) may subset the previously collected data (i.e., "history" data). The PC may be obtained by using conventional techniques such as Principal Component Analysis (PCA) transformation of collected vehicle speed data, operational data, and ambient weather data.

The regression routine may be a multivariate adaptive regression spline algorithm. The multivariate adaptive regression spline predicts the change in output based on a weighted sum of linear functions:

where P is the pressure of the refrigerant and,is a coefficient value, and->Is the hinge basis function. A "hinge base function" is a function that outputs only a portion of another function beyond a specified point (referred to as a "node"): />Wherein->Is a junction point and brackets indicate the hinge basis function +.>Outputting the positive value of the input. Coefficient value +_ can be determined by fitting a model to empirical data collected by a plurality of test vehicles 105 operating on a specified route>And hinge basis function->X _i Is the ith variable of vehicle speed data, ambient weather data, and operation data. That is, X represents all data for determining the pressure P, and for n total variables, X _i Is one of the variables such that 1.ltoreq.i.ltoreq.n, where i, n is a natural number. The "linear" function is a polynomial function of degree 1, i.e. a straight line. That is, the regression procedure is a "spline", i.e., a piecewise sum of pieces of a plurality of linear functions, each linear function being a variable X _i Scalar multiples of (c) and constants.

The multiple adaptive regression spline algorithm uses piecewise fit linear functions to capture the nonlinear dependence of the changes in the input on the changes in the output to generate a spline. The computer 110 may train a regression routine using the previously collected operational data, vehicle speed data, and ambient weather data to determine a particular weight and hinge function for each of the one or more variables based on the operational data, vehicle speed data, and ambient weather data. For example, the computer 110 may train a regression routine to output a predicted pressure of the refrigerant based on inputs of at least some of the variables described in table 1 below:

X _i	data type
		Refrigerant evaporating temperature	Operational data
Target evaporator temperature	Operational data
		Cooling fan rotational speed	Operational data
Blower rotational speed	Operational data
		Ambient outside air temperature	Weather data
Temperature difference between ambient outside air and evaporator target temperature	Weather data
		Speed of propulsion device	Velocity data
Wheel speed	Velocity data

Table 1: variables of regression program

FIG. 3 includes three graphs or charts 300, 305, 310 illustrating the computer 110 determining a baseline differential pressure for the climate control subsystem 135. The "baseline" differential pressure is the average of the differences between the predicted pressure output from the regression routine and the measured actual pressure. To detect small changes in baseline differential pressure, computer 110 determines an Exponentially Weighted Moving Average (EWMA), i.e., a recursively determined value based on the current predicted pressure and the previously determined value:

R _b，t ＝λR _t +(1-λ)R _b，t-1 (2)

wherein t indicates determining a baseline differential pressure R _b,t T-1 indicates the previous stroke, R _t Is the predicted pressure difference of the refrigerant of the current stroke t, R _b,t-1 Is the baseline pressure of the previous stroke t-1Difference, and λ is the control of the previous time differential pressure determination vs R _b,t And a weighting factor that affects the rate of false positive detection of leaks in the climate control subsystem 135 that the computer 110 may generate according to a regression routine. The weighting factor λ may be 0.05, i.e., the regression program may be trained to output a false positive identification rate of leakage at a rate of up to 5% recommended by the manufacturer. That is, the computer 110 may determine the data R by applying the first weight value λ to the collected data R _t And applies a second weight value 1-lambda to the previously determined data R _b,t-1 To generate a baseline differential pressure R _b,t 。

The computer 110 may be based on the average differential pressure μ of the refrigerant over multiple passes _m To update the baseline pressure difference R of the refrigerant _b . In this context, a "trip" is a specified period of time, typically from the start of the vehicle 105 to the stop of the vehicle 105. In performing m multiple passes (where m is a natural number), the computer 110 may determine a posterior baseline differential pressure μ _{Posterior test} ：

Wherein mu ₀ Is the average of the predicted pressure differences from the training dataset collected during the training regression routine,is the variance, μ of the predicted differential pressure from the training dataset _m Is the average of the predicted differential pressures for m strokes, and +.>Is the variance of the predicted differential pressure for m strokes. The computer 110 may calculate the baseline differential pressure R using the weighting factor λ _b,t Previously set baseline differential pressure R _b,0 ＝μ _{Posterior test} Is set to be a constant value. Thus, upon completion of each trip t, the computer 110 may compare the current baseline differential pressure R according to the weighting factor λ _b,t-1 Updated to a new value R _b,t As indicated above.

Computer 110The difference between the predicted pressure output from the regression routine and the actual pressure measured by the pressure sensor 115 may be determined. The pressure sensor 115 may measure the pressure of the refrigerant exiting the compressor 200 as the "actual" pressure of the refrigerant. Using the difference R between the predicted pressure and the actual pressure _t To calculate a new baseline differential pressure R _b,t . When the base line pressure difference R _b,t When the threshold is exceeded, the computer 110 may actuate the component 120 to account for leaks in the climate control subsystem 135. For example, the computer 110 deactivates the compressor 200. By disabling the compressor 200, the computer 110 may prevent unnecessary operation of the compressor 200, thereby extending the life of the compressor 200 and reducing potential maintenance costs. In another example, the computer 110 may provide an alert to an occupant of the vehicle 105 indicating a leak. The computer 110 may actuate lights and/or speakers and/or haptic devices to indicate a leak in the climate control subsystem 135. In another example, the computer 110 may send a message to an external server 130 (e.g., a server storing diagnostic data from multiple vehicles 105 of the manufacturer) indicating a leak in the climate control subsystem.

The threshold value may be based on the standard deviation sigma of the predicted output pressure P determined by inputting the training data into the regression program ₀ . That is, the computer 110 may be based on the standard deviation σ ₀ And updated baseline differential pressure R after the mth pass _b ，μ _{Posterior test} To determine the upper limit of pressure UL _t And lower limit LL _t ：

Where L is a control value determined to control the false positive detection rate below a manufacturer recommended limit. For example, when l=3, limit UL _t ,LL _t Based on the distance average mu _{Posterior test} Is a standard deviation of three.

FIG. 3 shows a baseline differential pressure R for multiple strokes t _t Is shown, is a graph 300, 305, 310. The vertical axis of each graph 300, 305, 310 is the pressure differential R _b,t And the horizontal axis of each graph 300, 305, 310 lists the travel t performed by the vehicle 105. That is, each point on each graph 300, 305, 310 is the EWMA differential pressure R for a particular stroke t _b,t Is a value of (2). Solid point indicates differential pressure R _b,t Limit UL at baseline differential pressure _t ,LL _t In, and the dotted line point indicates the pressure difference R _b,t Exceeding the limit UL _t ,LL _t One of which is a metal alloy.

In the example shown in graph 305, the differential pressure data begins to exceed the upper limit UL of the subsequent stroke _t . An increase in the differential pressure data indicates that the climate control subsystem 135 may generally be above the upper limit UL _t Indicating that climate control subsystem 135 includes more refrigerant than a typical climate control subsystem 135. Alternatively, the differential pressure data may drop below the lower limit LL _t As shown in graph 310. When the differential pressure data of the stroke approaches and falls below the lower limit LL _t When the computer 110 may determine that the climate control subsystem includes less refrigerant than a typical climate control subsystem 135, for example, based on leaks in the climate control subsystem 135.

When the predicted pressure and the actual pressure R _b,t The baseline differential pressure between drops below the threshold value during the run time exceeding the time threshold (e.g., lower limit LL _t ) In this regard, the computer 110 may actuate one or more of the components 120. That is, upon detecting a difference that exceeds a threshold, the computer 110 may start a timer and measure the amount of time that the difference exceeds the threshold. If the difference returns to below the threshold, the computer 110 may determine that no leakage has occurred and continue operation of the compressor 200. If the run time since the timer was started exceeds a time threshold, computer 110 may determine that a leak has occurred and deactivate compressor 200. The time threshold may be determined based on empirically tested pressure data from the climate control subsystem 135 having a particular leak. The time threshold may be that the pressure differential caused by leakage remains above the thresholdValues and will not return to a run time below the threshold value, for example 10 seconds.

Fig. 4 is a diagram of an exemplary process 400 for detecting leaks in the climate control subsystem 135 in the vehicle 105. Process 400 begins at block 405, where computer 110 actuates one or more sensors 115 to collect ambient weather data. As described above, the ambient weather data may include, for example, ambient air temperature, precipitation amount, precipitation type, wind speed, etc. of the air outside the vehicle. Computer 110 may receive at least some ambient weather data from server 130.

Next, at block 410, the computer 110 collects vehicle speed data. The vehicle speed data includes engine speed and wheel speed. That is, the computer 110 may collect rotational speed data of the internal combustion engine and rotational speed data of one of the wheels of the vehicle 105.

Next, at block 415, the computer 110 may collect operational data of the climate control subsystem 135. As described above, the computer 110 may collect data regarding the components of the climate control subsystem 135. The operation data may include, for example, a refrigerant evaporation temperature, a rotation speed of the cooling fan 210, a rotation speed of the blower fan 230, and the like.

Next, at block 420, the computer 110 inputs the collected data into a regression routine to output a predicted refrigerant pressure. As described above, the regression routine may be trained to correlate the input operation, speed, and weather data with refrigerant pressure. For example, the regression routine may be a multivariate adaptive regression spline algorithm that maps nonlinear changes in refrigerant pressure into a plurality of piecewise linear functions.

Next, at block 425, the computer 110 determines the actual refrigerant pressure. The computer 110 may actuate a pressure sensor 115 disposed in the climate control subsystem 135 to determine the actual refrigerant pressure. The actual refrigerant pressure may be the pressure of the refrigerant leaving the compressor 200.

Next, at block 430, the computer 110 determines whether the difference between the predicted refrigerant pressure and the actual refrigerant pressure exceeds a threshold. As described above, the threshold may be the maximum deviation from a baseline differential pressure determined from previously collected pressure data. If the difference between the predicted refrigerant pressure and the actual refrigerant pressure falls below the threshold, process 400 continues at block 435. Otherwise, the process 400 continues at block 440.

At block 435, the computer 110 actuates one or more components 120. For example, the computer 110 may deactivate the compressor 200 of the climate control subsystem 135. Because the compressor 200 compresses the refrigerant, the compressor 200 may operate at a higher rate to compress the leaked refrigerant to a specified pressure. By disabling the compressor 200, the computer 110 may prevent unnecessary operation of the compressor 200, thereby extending the life of the compressor 200 and reducing potential maintenance costs. In another example, the computer 110 may actuate a speaker and/or light to provide an audio and/or visual alert to an occupant of the vehicle 105.

At block 440, computer 110 determines whether to continue process 400. For example, if computer 110 has deactivated compressor 200, computer 110 may determine not to continue process 400. If computer 110 determines to continue, process 400 returns to block 405. Otherwise, the process 400 ends.

The computing devices discussed herein, including computer 110, include a processor and a memory, each of which typically includes instructions capable of being executed by one or more computing devices, such as the computing devices identified above, and for performing the blocks or steps of the processes described above. Computer-executable instructions may be compiled or interpreted by a computer program created using a variety of programming languages and/or techniques, including but not limited to Java, alone or in combination ^TM C, C ++, visual Basic, java Script, python, perl, HTML, etc. In general, a processor (e.g., a microprocessor) receives instructions, e.g., from a memory, a computer-readable medium, etc., and executes the instructions, thereby performing one or more processes, including one or more of the processes described herein. Such instructions and other data may be stored and transmitted using a variety of computer-readable media. Files in computer 110 generally refer to a collection of data stored on a computer readable medium such as a storage medium, random access memory, or the like.

Computer-readable media include any medium that participates in providing data (e.g., instructions) that may be read by a computer. Such a medium may take many forms, including but not limited to, non-volatile media, and the like. Non-volatile media includes, for example, optical or magnetic disks and other persistent memory. Volatile media includes Dynamic Random Access Memory (DRAM), which typically constitutes a main memory. Common forms of computer-readable media include, for example, a floppy disk, a flexible disk, hard disk, magnetic tape, any other magnetic medium, a CD ROM, DVD, any other optical medium, punch cards, paper tape, any other physical medium with patterns of holes, RAM, PROM, EPROM, a flash EEPROM, any other memory chip or cartridge, or any other medium from which a computer can read.

With respect to the media, processes, systems, methods, etc. described herein, it should be understood that although the steps of such processes, etc. have been described as occurring in some ordered sequence, such processes may be practiced by performing the described steps in an order different than the order described herein. It should also be understood that certain steps may be performed concurrently, other steps may be added, or certain steps described herein may be omitted. For example, in process 400, one or more of the steps may be omitted, or the steps may be performed in a different order than shown in fig. 4. In other words, the description of systems and/or processes herein is provided to illustrate certain embodiments and should not be taken in any way as limiting the disclosed subject matter.

Accordingly, it is to be understood that the disclosure, including the foregoing description and drawings, and the appended claims is intended to be illustrative, but not limiting. Many embodiments and applications other than the examples provided will be apparent to those of skill in the art upon reading the above description. The scope of the invention should be determined, not with reference to the above description, but should instead be determined with reference to the appended claims, along with the full scope of equivalents to which such claims are entitled, and/or on the basis of the claims that are included in the non-provisional patent application. It is contemplated and anticipated that future developments will occur in the arts discussed herein, and that the disclosed systems and methods will be incorporated into such future embodiments. In sum, it should be understood that the disclosed subject matter is capable of modification and variation.

The articles "a" and "an" of a modified noun should be understood to mean one or more, unless otherwise indicated or otherwise required by the context. The phrase "based on" encompasses being partially or completely based on.

According to the present invention there is provided a system having a computer comprising a processor and a memory, the memory storing instructions executable by the processor to: collecting environmental (a) weather data, (b) vehicle speed data including at least one of vehicle speed or engine speed, and (c) operational data of a climate control subsystem of the vehicle; inputting the collected data into a regression program trained to output predicted refrigerant pressure of the climate control subsystem, the regression program trained with previously determined ambient weather data, previous vehicle speed or previous engine speed data, and previous operating data of the climate control subsystem; determining the actual pressure of the refrigerant in the climate control subsystem; and actuating a component upon determining that the difference between the predicted pressure and the actual pressure falls below a threshold.

According to an embodiment, the instructions further comprise instructions to: the regression routine is retrained using the collected data and the previously determined data by applying a first weight value to the collected data and a second weight value to the previously determined data, the first weight value being greater than the second weight value.

According to an embodiment, the instructions further comprise instructions to: the predicted pressure is output based on a plurality of previously predicted pressure differentials of the refrigerant of the climate control subsystem.

According to an embodiment, the instructions further comprise instructions to: each of the plurality of previously predicted differential pressures is determined as a respective average of the predicted differential pressures during previous respective trips, each trip being a period of time between activation of the vehicle and deactivation of the vehicle.

According to an embodiment, the threshold value is based on a standard deviation of the plurality of previously predicted differential pressures from an average of the previously predicted differential pressures.

According to an embodiment, the threshold value is further based on a false positive rate of the predicted pressure indicative of the refrigerant leakage in the climate control subsystem.

According to an embodiment, the instructions further comprise instructions to: the difference between the predicted pressure and the actual pressure is determined based on a predicted false positive rate of the predicted pressure indicative of a leak in the climate control subsystem.

According to an embodiment, the operational data of the climate control subsystem includes a blower speed and an evaporation temperature of the refrigerant.

According to an embodiment, the instructions further comprise instructions to: a baseline pressure differential of the refrigerant of the climate control subsystem is determined based on the previous operating data of the climate control subsystem.

According to an embodiment, the instructions further comprise instructions to: the reference pressure difference of the refrigerant is updated based on an average pressure difference between the predicted pressure of the refrigerant and the actual pressure of the refrigerant during a period from activation of the vehicle to deactivation of the vehicle.

According to an embodiment, the instructions further comprise instructions to: the component is actuated when the difference between the predicted pressure and the actual pressure exceeds the threshold for a run time exceeding a time threshold.

According to an embodiment, the regression program is a multivariate adaptive regression spline.

According to an embodiment, the instructions to actuate the component comprise instructions to deactivate a compressor of the climate control subsystem.

According to the invention, a method comprises: collecting (a) ambient weather data, (b) vehicle speed data including at least one of a vehicle speed or an engine speed, and (c) operational data of a climate control subsystem of the vehicle; inputting the collected data into a regression program trained to output predicted refrigerant pressure of the climate control subsystem, the regression program trained with previously determined ambient weather data, previous vehicle speed or previous engine speed data, and previous operating data of the climate control subsystem; determining the actual pressure of the refrigerant in the climate control subsystem; and actuating a component upon determining that the difference between the predicted pressure and the actual pressure falls below a threshold.

In one aspect of the invention, the method includes retraining the regression program using the collected data and the previously determined data by applying a first weight value to the collected data and a second weight value to the previously determined data, the first weight value being greater than the second weight value.

In one aspect of the invention, the method includes outputting the predicted pressure based on a plurality of previously predicted pressures of the refrigerant of the climate control subsystem.

In one aspect of the invention, the method includes determining each of the plurality of previously predicted pressures as a respective average of predicted pressures during previous respective trips, each trip being a period of time between activation of the vehicle and deactivation of the vehicle.

In one aspect of the invention, the threshold is based on a standard deviation of the plurality of previously predicted pressures from an average of the previously predicted pressures.

In one aspect of the invention, the method includes determining the difference between the predicted pressure and the actual pressure based on a predicted false positive rate of the predicted pressure indicative of a leak in the climate control subsystem.

In one aspect of the invention, the method includes disabling a compressor of the climate control subsystem upon determining that the difference between the predicted pressure and the actual pressure falls below the threshold.

Claims

1. A method, comprising:

collecting (a) ambient weather data, (b) vehicle speed data including at least one of a vehicle speed or an engine speed, and (c) operational data of a climate control subsystem of the vehicle;

inputting the collected data into a regression program trained to output predicted refrigerant pressure of the climate control subsystem, the regression program trained with previously determined ambient weather data, previous vehicle speed or previous engine speed data, and previous operating data of the climate control subsystem;

determining the actual pressure of the refrigerant in the climate control subsystem; and

actuating a component upon determining that a difference between the predicted pressure and the actual pressure falls below a threshold.

2. The method of claim 1, further comprising retraining the regression program using the collected data and the previously determined data by applying a first weight value to the collected data and a second weight value to the previously determined data, the first weight value being greater than the second weight value.

3. The method of claim 1, further comprising outputting the predicted pressure based on a plurality of previously predicted differential pressures of the refrigerant of the climate control subsystem.

4. The method of claim 3, further comprising determining each of the plurality of previously predicted differential pressures as a respective average of predicted differential pressures during previous respective trips, each trip being a period of time between activation of the vehicle and deactivation of the vehicle.

5. The method of claim 4, wherein the threshold is based on a standard deviation of the plurality of previously predicted differential pressures from an average of the previously predicted differential pressures.

6. The method of claim 5, wherein the threshold is further based on a false positive rate of the predicted pressure indicative of the refrigerant leak in the climate control subsystem.

7. The method of claim 1, further comprising determining the difference between the predicted pressure and the actual pressure based on a predicted false positive rate of the predicted pressure indicative of a leak in the climate control subsystem.

8. The method of claim 1, wherein the operational data of the climate control subsystem includes a blower speed and an evaporation temperature of the refrigerant.

9. The method of any of claims 1-8, further comprising determining a baseline pressure differential of the refrigerant of the climate control subsystem based on the previous operating data of the climate control subsystem.

10. The method of claim 9, further comprising updating the baseline pressure differential of the refrigerant based on an average pressure differential between the predicted pressure of the refrigerant and the actual pressure of the refrigerant during a period from activation of the vehicle to deactivation of the vehicle.

11. The method of any one of claims 1 to 8, further comprising actuating the component when the difference between the predicted pressure and the actual pressure exceeds a time threshold for a run time exceeding the threshold.

12. The method of any of claims 1-8, further comprising disabling a compressor of the climate control subsystem upon determining that the difference between the predicted pressure and the actual pressure falls below the threshold.

13. A computer programmed to perform the method of any one of claims 1 to 8.

14. A vehicle comprising the computer of claim 13.

15. A computer program product comprising a computer readable medium storing instructions executable by a computer processor to perform the method of any one of claims 1 to 8.