WO2018094929A1 - Procédé et appareil d'estimation de température - Google Patents

Procédé et appareil d'estimation de température Download PDF

Info

Publication number
WO2018094929A1
WO2018094929A1 PCT/CN2017/078197 CN2017078197W WO2018094929A1 WO 2018094929 A1 WO2018094929 A1 WO 2018094929A1 CN 2017078197 W CN2017078197 W CN 2017078197W WO 2018094929 A1 WO2018094929 A1 WO 2018094929A1
Authority
WO
WIPO (PCT)
Prior art keywords
temperature
neural network
network model
test
input
Prior art date
Application number
PCT/CN2017/078197
Other languages
English (en)
Chinese (zh)
Inventor
张俊彪
Original Assignee
华为技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 华为技术有限公司 filed Critical 华为技术有限公司
Priority to CN201780005080.1A priority Critical patent/CN108474823B/zh
Publication of WO2018094929A1 publication Critical patent/WO2018094929A1/fr

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
    • G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
    • G01R31/36—Arrangements for testing, measuring or monitoring the electrical condition of accumulators or electric batteries, e.g. capacity or state of charge [SoC]

Definitions

  • the present application relates to the field of communications, and in particular, to a method and apparatus for estimating temperature.
  • a rechargeable electronic device (eg, a mobile phone) includes components such as a battery and a charging chip, wherein the battery includes a battery cell.
  • the processor can take certain protective measures to reduce the temperature of the battery core when determining the temperature of the battery core to reach the threshold value, thereby achieving temperature protection of the battery core.
  • the processor of the mobile phone can limit the charging current by controlling the charging chip when determining that the battery temperature is greater than 45 ° C (degree Celsius), so as to achieve the purpose of lowering the temperature of the battery core; when the mobile phone is discharged, the mobile phone The processor can start the shutdown process to stop the battery discharge when the cell temperature is determined to be greater than 60 ° C, thereby achieving the purpose of lowering the cell temperature.
  • the cell temperature in order to achieve temperature protection of the cell, the cell temperature must be obtained in real time. At present, the cell temperature cannot be directly measured and can only be obtained by an estimation method. Specifically, a negative temperature coefficient (NTC) thermistor can be placed on the protection board of the battery. In this way, the rechargeable electronic device can determine the temperature of the protection board according to the detected resistance value of the NTC thermistor, and approximate the temperature of the battery core by using the determined temperature of the protection board, that is, determine the temperature of the protection board as the battery core. temperature.
  • the protective plate is usually provided with a positive temperature coefficient (PTC) thermistor and a metal oxide semiconductor (MOS) tube.
  • the PTC When the charging current or the discharging current is small, the PTC is thermally sensitive. The resistor and the MOS tube do not substantially heat up, and the temperature of the protection board is close to the temperature of the battery core. At this time, it is reasonable to use the temperature of the protection board to approximate the temperature of the battery core. However, in the case of a large charging current or a large discharging current, the heat generated by the PTC thermistor and the MOS tube is large, and the temperature of the protection board is much higher than the temperature of the battery core. In this case, if the protection board is still used. The temperature approximates the cell temperature and causes the estimated cell temperature to be inaccurate.
  • the estimation of the cell temperature can be made more accurate by rough compensation.
  • the charging current is 3 amps (A)
  • the temperature of the protective plate is actually measured to be 12 ° C higher than the cell temperature.
  • the compensation amount is 5 ° C, that is, a safety margin of 7 ° C is required.
  • the rechargeable electronic device can subtract the temperature of the obtained protection board by 5 ° C when the charging current is determined to be 3 A to obtain the battery core temperature.
  • the prior art compensation algorithm needs to leave a large safety margin when setting the compensation amount, which will cause the estimated battery temperature of the rechargeable electronic device to remain. However, there is a large deviation.
  • the present application provides a method and apparatus for estimating temperature, which solves the problem that the estimated cell temperature of the rechargeable electronic device has a large deviation.
  • a method of estimating temperature comprising:
  • the effective temperature set includes M effective temperatures, M is an integer greater than or equal to 0, and less than or equal to N.
  • M is greater than 0 and less than or equal to N
  • the corresponding effective temperature is tested according to each of the M effective temperatures.
  • the position in the component determines the target neural network model from the set of neural network models and determines the temperature of the component to be estimated at the target location based on the M effective temperature and the target neural network model.
  • the neural network model set includes: single input neural network model, two input neural network model, ..., i input neural network model, ..., N-1 input neural network model, N input neural network model, i is greater than or equal to 1 And an integer less than or equal to N.
  • the i-input neural network model is a model in which the number of input variables obtained by the neural network algorithm is i, and the input variable contained in the i-input neural network model corresponds to any i positions in the N positions, and the target neural network model Enter the neural network model for M.
  • the method for estimating temperature detects the temperature of the component at each of the N locations, and after obtaining the test temperature set, the effective temperature set including the M effective temperatures can be determined from the test temperature set.
  • M is greater than 0 and less than or equal to N
  • the target neural network model is determined from the neural network model set according to the position of each of the M effective temperatures corresponding to the position in the test component, and according to the M effective temperatures and targets
  • the neural network model determines the temperature of the component to be estimated at the target location.
  • the neural network model of causality estimates the temperature of the cell, and therefore the deviation of the temperature of the cell estimated by the method of estimating temperature of the present application is compared with the estimation of the temperature of the cell by the coarse compensation algorithm in the prior art. Smaller.
  • the cell temperature is performed only by the temperature of the effective test component, that is, the effective temperature. Estimation further improves the accuracy of the estimated cell temperature.
  • determining the effective temperature set from the test temperature set may include: determining, for each test temperature in the test temperature set, whether the test temperature is greater than a first preset threshold. And being less than the second preset threshold, and determining that the test temperature is greater than the first preset threshold and less than the second predetermined threshold, determining that the test temperature is an effective temperature to determine an effective temperature set.
  • the target neural network model is determined from the neural network model set according to the position of each of the M effective temperatures corresponding to the test component.
  • the method may include: determining, according to the position and the first mapping relationship of each valid temperature in the M effective temperature, the input variable set, and determining the target neural network model according to the input variable set and the second mapping relationship.
  • the input variable set includes M input variables
  • the first mapping relationship includes a position and an input variable corresponding to each valid temperature in the M effective temperatures in the test component.
  • the second mapping relationship includes a correspondence between the input variable set and the target neural network model.
  • the method for estimating temperature provided by the present application may further include: displaying prompt information when M is equal to 0; or, when M is equal to 0 Start the shutdown program; or, when M is equal to 0, display a prompt message and start the shutdown procedure.
  • the prompt information is used to prompt the user to perform temperature estimation. In this way, the user can know the fault information to perform maintenance of the equipment, thereby avoiding the problem that the component to be estimated has a safety hazard due to the inability to estimate the temperature of the component to be estimated.
  • the target neural network is determined from the set of neural network models according to the position of each effective temperature in the test component according to the M effective temperatures.
  • the method may further include: determining a neural network model set.
  • determining a neural network model set may specifically include: acquiring, for an i input neural network model, a sample temperature set including a temperature of the X group of samples, X is an integer greater than or equal to 1, the sample temperature includes a sample temperature of a test component at each of any of the N positions, and a sample temperature of the component to be estimated at the target location; and using neural network algorithms and samples The temperature set determines the i-input neural network model to determine the neural network model set.
  • an apparatus for estimating a temperature comprising: a test component, a component to be estimated, and a processor.
  • a processor for invoking an instruction stored in the memory to: collect a temperature of the test component at each of the N locations, obtain a test temperature set, N is an integer greater than or equal to 2, and the test temperature set includes N Testing temperature; determining an effective temperature set from the set of test temperatures, the effective temperature set includes M effective temperatures, M is an integer greater than or equal to 0, and less than or equal to N; when M is greater than 0 and less than or equal to N,
  • the target neural network model is determined from the neural network model set according to the position of each of the M effective temperatures corresponding to the test component; the temperature of the component to be estimated at the target location is determined according to the M effective temperature and the target neural network model.
  • the neural network model set includes: single input neural network model, two input neural network model, ..., i input neural network model, ..., N-1 input neural network model, N input neural network model, i is greater than or equal to 1
  • the i-input neural network model is a model in which the number of input variables obtained by the neural network algorithm is i, and the input variable contained in the i-input neural network model and any i positions in the N positions are one by one.
  • the target neural network model is an M input neural network model.
  • the processor is specifically configured to: determine, for each test temperature in the test temperature set, whether the test temperature is greater than a first preset threshold and less than a second preset threshold, When it is determined that the test temperature is greater than the first preset threshold and less than the second preset threshold, the test temperature is determined to be an effective temperature to determine an effective temperature set.
  • the processor is specifically configured to: correspond to a location and a first mapping relationship in the test component according to each of the M effective temperatures. Determining an input variable set, the input variable set includes M input variables, and the first mapping relationship includes a correspondence between each valid temperature of the M effective temperatures corresponding to the position in the test component and the input variable; according to the input variable set and The second mapping relationship determines a target neural network model, and the second mapping relationship includes a correspondence between the input variable set and the target neural network model.
  • the device for estimating temperature further includes a display, when M is equal to 0, the display is configured to display prompt information, and the prompt information is used to prompt the user to Performing temperature estimation; or, the device for estimating temperature further includes a display, when M is equal to 0, the display is for displaying prompt information, the processor is also used to start the shutdown program; or, when M is equal to 0, the processor is further Used to start the shutdown program.
  • the processor is further configured to: determine a neural network model set.
  • the processor is specifically configured to: obtain, for the i input neural network model, a sample temperature set, where the sample temperature set includes the X group sample temperature, X is an integer greater than or equal to 1, and the sample temperature includes a sample temperature of a test component at each of any of the N positions and a sample temperature of the component to be estimated at the target location; using a neural network algorithm and a sample temperature set The i-input neural network model is determined to determine a neural network model set.
  • the test component may be at least one of the following: a protection board for a battery, a universal serial bus (USB) small board of a mobile phone,
  • USB universal serial bus
  • the mobile phone motherboard, the component to be estimated can be the battery cell or the phone case.
  • a computer storage medium for storing computer software instructions for use in a device for estimating temperature as described above, the computer software instructions comprising a program designed to perform the method of estimating temperature described above.
  • 1 is a schematic diagram of the composition of a mobile phone provided by the present application.
  • FIG. 3 is a flow chart of another method for estimating temperature provided by the present application.
  • FIG. 4 is a schematic diagram of deployment of an NTC resistor in a mobile phone provided by the present application.
  • FIG. 5 is a schematic diagram of a neural network model provided by the present application.
  • FIG. 6 is a schematic diagram of another neural network model provided by the present application.
  • Figure 7 is a schematic diagram showing the composition of a device for estimating temperature provided by the present application.
  • FIG. 8 is a schematic structural diagram of another apparatus for estimating temperature provided by the present application.
  • FIG. 9 is a schematic diagram showing the composition of another temperature estimating device provided by the present application.
  • the present application provides a method for estimating the temperature, the basic principle is: collecting the temperature of the test component at each of the N positions, and obtaining the test.
  • a temperature set N is an integer greater than or equal to 2
  • an effective temperature set containing M effective temperatures is determined from the set of test temperatures
  • M is an integer greater than or equal to 0 and less than or equal to N, when M is greater than 0,
  • the target neural network model is determined from the neural network model set, and the target is determined according to the M effective temperature and the target neural network model.
  • the neural network model set includes: Single input neural network model, two input neural network model, ..., i input neural network model, ..., N-1 input neural network model, N input neural network model, i is an integer greater than or equal to 1, and less than or equal to N
  • the i input neural network model is a model in which the number of input variables obtained by the neural network algorithm is i, and the input variable included in the i input neural network model corresponds to any i positions in the N positions, and the target neural network model is M input neural network model.
  • the neural network model of causality estimates the temperature of the cell, and therefore the deviation of the temperature of the cell estimated by the method of estimating temperature of the present application is compared with the estimation of the temperature of the cell by the coarse compensation algorithm in the prior art. Smaller.
  • the cell temperature is performed only by the temperature of the effective test component, that is, the effective temperature. Estimation further improves the accuracy of the estimated cell temperature.
  • the method for estimating temperature can be applied to a device including a device for estimating temperature, and the device can be a rechargeable electronic device such as a mobile phone, a tablet computer, a notebook computer or the like.
  • the present application uses a rechargeable electronic device as a mobile phone as an example for description.
  • FIG. 1 is a schematic diagram of a composition of a mobile phone provided by the present application.
  • the mobile phone may include a battery 10 , a mobile phone USB small board 11 , a touch screen 12 , a processor 13 , a memory 14 , and a radio frequency (Radio ) Frequency, RF) circuit 15, gravity sensor 16, audio circuit 17, speaker 18, microphone 19 and other components, these components can be connected by bus or directly.
  • Radio radio frequency
  • RF radio frequency
  • the battery 10 is logically connected to the processor 13 through a power management system to implement functions such as charging, discharging, and power consumption management through the power management system.
  • Battery 10 can include a battery cell and a protective plate.
  • the mobile phone USB small board 11 is the main board of the charging interface.
  • the touch screen 12 can be referred to as a touch display panel for realizing the input and output functions of the mobile phone, and can collect touch operations on or near the user (for example, the user uses any suitable object or accessory such as a finger or a stylus to touch The operation on the control panel 12 or in the vicinity of the touch screen 12) and driving the corresponding connection device according to a preset program. It can also be used to display information entered by the user or information provided to the user (such as images captured by the camera) as well as various menus of the mobile phone.
  • the touch screen 12 may include a display module 121.
  • the display module 121 can display prompt information for prompting the user not to perform temperature estimation.
  • the processor 13 is the control center of the handset, which connects various portions of the entire handset using various interfaces and lines, by executing or executing software programs and/or modules stored in the memory 14, and invoking data stored in the memory 14, executing The phone's various functions and processing data, so that the overall monitoring of the phone.
  • the processor 13 may include one or more processing units; the processor 13 may integrate an application processor and a modem processor.
  • the application processor mainly processes an operating system, a user interface, an application, and the like, and the modem processor mainly processes wireless communication. It can be understood that the above modem processor may not be integrated into the processor 13.
  • the processor 13 may collect the temperature of the test component at each of the N locations, and determine the effective temperature set from the test temperature set, and Based on the position of each of the M effective temperatures corresponding to the position in the test component, the target neural network model is determined from the neural network model set, and the temperature of the component to be estimated at the target position is determined according to the M effective temperature and the target neural network model.
  • the memory 14 can be used to store data, software programs, and modules, and can be a Volotile Memory, such as a Random-Access Memory (RAM), or a Non-Volatile Memory.
  • a Volotile Memory such as a Random-Access Memory (RAM), or a Non-Volatile Memory.
  • RAM Random-Access Memory
  • Non-Volatile Memory a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid state drive (SSD); or a combination of the above types of memories.
  • the program 14 can store program code for causing the processor 13 to execute the method for estimating the temperature provided by the present application by executing the program code.
  • the RF circuit 15 can be used for transmitting and receiving information or during a call, receiving and transmitting signals, and in particular, processing the received information to the processor 13; in addition, transmitting the signal generated by the processor 13.
  • the RF circuit 15 includes, but is not limited to, an antenna, at least one amplifier, a transceiver, a coupler, a Low Noise Amplifier (LNA), a duplexer, and the like.
  • the RF circuit 15 can also communicate with the network and other devices through wireless communication.
  • Gravity Sensor 16 can detect the acceleration of the mobile phone in all directions (usually three-axis). When it is still, it can detect the magnitude and direction of gravity. It can be used to identify the gesture of the mobile phone (such as horizontal and vertical screen switching, related Game, magnetometer attitude calibration), vibration recognition related functions (such as pedometer, tapping). It should be noted that the mobile phone 10 may further include other sensors, such as a pressure sensor, a light sensor, a gyroscope, a barometer, a hygrometer, a thermometer, an infrared sensor, and the like, and details are not described herein.
  • Audio circuitry 17, speaker 18, and microphone 19 provide an audio interface between the user and the handset.
  • the audio circuit 17 can transmit the converted electrical data of the received audio data to the speaker 18 for conversion to the sound signal output by the speaker 18; on the other hand, the microphone 19 converts the collected sound signal into an electrical signal by the audio circuit 17 After receiving, it is converted into audio data, and then the audio data is output to the RF circuit 15 for transmission to, for example, another mobile phone, or the audio data is output to the processor 13 for further processing.
  • components such as processor 13, memory 14, RF circuitry 15, gravity sensor 16, and audio circuitry 17 may be deployed on the handset motherboard.
  • the mobile phone may also include a Wireless Fidelity (WiFi) module, a Bluetooth module, a camera, a mobile phone casing, and the like, and will not be described again.
  • WiFi Wireless Fidelity
  • components that cannot directly collect temperature in the mobile phone can be used as components to be estimated, such as a battery core and a mobile phone casing, and components that can directly collect temperature in the mobile phone can be used as test components, such as , protection board, mobile phone USB small board and mobile phone motherboard.
  • the mobile phone can use the temperature of the test component to estimate the temperature of the component to be estimated.
  • at least one of a protection board, a mobile phone USB small board, and a mobile phone main board may be used as a test component to estimate the temperature of the component to be estimated.
  • a temperature sensor is only deployed on the mobile phone USB small board to estimate the temperature of the phone case; or, only a temperature sensor is deployed on the protection board to estimate the temperature of the battery cell; or, in the mobile phone USB board and Temperature sensors are respectively deployed on the mobile phone motherboard to estimate the temperature of the battery cells; or temperature sensors are respectively deployed on the protection board and the mobile phone motherboard to estimate the temperature of the mobile phone case; or, in the protection board, the mobile phone USB small board And hand Temperature sensors are separately deployed on the main board to estimate the temperature of the cells.
  • the embodiment of the present application does not specifically limit the kind of specific components included in the test component.
  • the method may include:
  • test temperature set Collect the temperature of the test component at each of the N locations to obtain a test temperature set.
  • test temperature set includes N test temperatures.
  • a temperature sensor such as an NTC resistor
  • NTC resistor can be separately deployed at N different locations on the test component, so that the rechargeable electronic device can pass The parameters of the temperature sensor at each location are read to obtain the temperature of the test component at each location, ie the test temperature is obtained.
  • N temperature sensors can be deployed on one test component or on multiple different test components.
  • M is an integer greater than or equal to 0 and less than or equal to N. Because the temperature of the temperature sensor is abnormal, the test temperature obtained from the temperature sensor reading will also be abnormal. If the temperature of the component to be estimated is still estimated by using the obtained test temperature, the estimated temperature will be greatly deviated, so To avoid the problem that the estimated temperature of the component to be estimated has a large deviation due to the temperature abnormality, after the rechargeable electronic device obtains the test temperature set, the effective temperature set can be determined from the test temperature set to remove the abnormal temperature. The effective temperature is the temperature collected by the rechargeable electronic device when the temperature sensor is normal.
  • the target neural network model is determined from the neural network model set according to the position of each of the M effective temperatures corresponding to the test component.
  • the neural network model set includes: single input neural network model, two input neural network model, ..., i input neural network model, ..., N-1 input neural network model, N input neural network model, i is greater than or equal to 1 And an integer less than or equal to N.
  • the model with the number of input variables obtained by the neural network algorithm is i
  • the input variable included in the i-input neural network model is in one-to-one correspondence with any i positions of the N positions.
  • the rechargeable electronic device may correspond to the position in the test component according to each of the M effective temperatures, from the neural network model set.
  • the M input neural network model is determined, which is a target neural network model, which contains M input variables, and M input variables are in one-to-one correspondence with M positions.
  • the method for estimating temperature detects the temperature of the component at each of the N locations, and after obtaining the test temperature set, the effective temperature set including the M effective temperatures can be determined from the test temperature set.
  • M is greater than 0 and less than or equal to N
  • the target neural network model is determined from the neural network model set according to the position of each of the M effective temperatures corresponding to the position in the test component, and according to the M effective temperatures and targets
  • the neural network model determines the temperature of the component to be estimated at the target location. In this way, when the temperature of the battery of the rechargeable electronic device is estimated by the method of estimating the temperature, the rechargeable battery is used.
  • the sub-device estimates the temperature of the cell based on the temperature of the test component and the neural network model capable of reacting the temperature between the component and the cell temperature in real time. Therefore, the cell is estimated using a coarse compensation algorithm in the prior art.
  • the deviation of the temperature of the cell estimated by the method of estimating the temperature of the present application is small compared to the temperature.
  • the cell temperature is performed only by the temperature of the effective test component, that is, the effective temperature. Estimation further improves the accuracy of the estimated cell temperature.
  • FIG. 3 is a flowchart of another method for estimating temperature provided by the present application. As shown in FIG. 3, the method may include:
  • the rechargeable electronic device is used as the mobile phone
  • the component to be estimated is the battery core
  • the test component is the protection board and the mobile phone USB small board, that is, the temperature of the protection board and the mobile phone USB small board are utilized.
  • the temperature is estimated by estimating the temperature of the cell as an example of the method of estimating the temperature.
  • the temperature sensor is an NTC resistor, as shown in FIG. 4, which is a schematic diagram of the deployment of the NTC resistor in the mobile phone.
  • One NTC resistor is disposed at the position A of the protection board, and the other NTC resistor is disposed at the position B of the USB board of the mobile phone.
  • the temperature at the position A can be used as the temperature of the protection board
  • the temperature at the position B can be used as the temperature of the USB board of the mobile phone
  • the temperature at the target position C can be used as the temperature of the battery core, that is, the position A is used.
  • the temperature at the temperature and the temperature at the position B is estimated as the temperature at the target position C as the temperature of the cell.
  • the mobile phone acquires a neural network model set.
  • the NTC resistor is placed on the cell to directly obtain the temperature of the cell.
  • the NTC resistor can be set on the mobile phone protection board and the mobile phone USB small board.
  • the temperature of the protection board and the temperature of the mobile phone USB small board can be directly obtained, and the temperature of the battery core and the temperature of the protection board and the USB small board of the mobile phone are The temperature has a causal relationship, so in the scenario where the temperature of the cell needs to be known, the temperature of the cell can be estimated using the temperature of the protection board and the temperature of the USB board of the mobile phone.
  • the handset can estimate the target position C using the temperature at position A and the temperature at position B ( The target position C is the temperature at a position of the cell to obtain the temperature of the cell.
  • the mobile phone Before estimating the temperature of the battery, the mobile phone needs to know the causal relationship between the temperature of the battery and the temperature of the protection board and the temperature of the USB board of the mobile phone.
  • the causal relationship between the temperature of the cell and the temperature of the protection board and the temperature of the USB board of the mobile phone can be represented by a neural network model.
  • the neural network model may be pre-stored in the handset, or the handset may be received by the modeling device (which may be a computer). That is to say, when the mobile phone needs to estimate the temperature of the battery core, the pre-stored neural network model can be obtained, and the neural network model sent by the modeling device can also be received.
  • the modeling device determines whether it is a pre-stored neural network model or a received neural network model.
  • the process by which the modeling device determines the neural network model is: the modeling device establishes a neural network model using a neural network algorithm and a sample temperature set.
  • the neural network model is used to indicate the causal relationship between the temperature of the cell and the temperature of the protection board and the temperature of the USB board of the handset.
  • the neural network since the NTC resistance set at the position A and the NTC resistance set at the B may be abnormal, in order to cause an abnormality in the NTC resistance, the neural network may still be used.
  • the network model determines the temperature of the battery cell.
  • the modeling device needs to determine a neural network model set, and the neural network model set needs to include: an abnormality occurs in the NTC resistor set at the position A, that is, only in the setting
  • the neural network model at the normal NTC resistance at B, the NTC resistance at position B is abnormal, that is, the neural network model only when the NTC resistance at A is normal.
  • the neural network model set also needs to be included.
  • the neural network model set needs to include: two single input neural network models and one two input neural network model.
  • the modeling device may first obtain a sample temperature set, where the sample temperature set includes X (X is an integer greater than or equal to 1) set of sample temperatures, and each set of sample temperatures The sample temperature of the test component at each of any of the two locations and the sample temperature of the cell at the target location C are included, and then the neural network algorithm and the sample temperature set are used to determine the i-input neural network model to determine the nerve A collection of network models.
  • the weight, c 1 is the offset
  • the input variable X 1 corresponds to the position A, as shown in FIG. 5, which is a schematic diagram of the model.
  • the input variable X 2 corresponds to position B.
  • two single-input neural network models and one two-input neural network model can be determined in the following manner.
  • the modeling device may acquire a sample temperature set including the X group sample temperature, wherein each set of sample temperature includes a sample temperature of the protection plate at the position A and a temperature of the battery cell at the target position C.
  • the modeling device may obtain a sample temperature set including X sets of sample temperatures from the pre-stored Table 1, each set of sample temperatures including the sample temperature of the protection plate at the position A at the same time and the target position C The sample temperature of the cell.
  • the table 1 may be pre-stored in the modeling device.
  • Table 1 acquisition The process may be: during a certain period of time, the mobile phone can collect the temperature of the protection board at the position A and the temperature of the mobile phone USB small board at the position B in real time, so that the user can obtain the position A at multiple times in the time period. The sample temperature of the protection board and the sample temperature of the mobile phone USB board at position B. And during this time period, the user can measure the temperature at the target position C by using the temperature measuring device to obtain the sample temperature of the battery cell at the target position C at a plurality of times in the time period.
  • the user can select the sample temperature of the protection board at position A at the same time, the sample temperature of the mobile phone USB small plate at position B, and the sample temperature of the battery at the target position C from all the sample temperatures obtained, and
  • the form shown in Table 1 is stored in the modeling device.
  • the neural network algorithm may include a linear regression method, a trapezoidal descent method, and the like, and the embodiment of the present application does not limit the neural network algorithm used herein.
  • a single input neural network model is established by using a linear regression method as an example for description.
  • the values of the parameters a 1 and c 1 can be used to obtain the unknown.
  • the sum of squared residuals Q is defined as:
  • the formula for the partial derivative of Q is 0:
  • the sample regression model obtained by the least squares method is:
  • the position with the highest temperature on the battery core needs to be the target position C, so that the problem that the safety of the battery is dangerous when the other positions on the battery core are used as the target position C can be avoided.
  • the other position on the cell the other position on the cell except the highest temperature position
  • the temperature of the cell at the highest temperature is higher than the threshold, but other positions are The temperature of the battery core does not reach the threshold.
  • the temperature measuring device may be manually used to measure the temperature at multiple positions on the battery to find the highest temperature position on the battery and mark it. The position where the temperature of the mark is the highest is the target position C.
  • the neural network model set in the charging state and the neural network model set in the discharging state are respectively established, and the neural network model set in the charging state and the neural network model set in the discharging state are preset in the mobile phone.
  • the temperature of the protection board at the location A of the mobile phone and the temperature of the USB small board of the mobile phone at the position B are obtained, and the test temperature set is obtained.
  • the voltage value of the NTC resistor set at the position A and the position B may be read first, and the resistance value is calculated according to the voltage value, and Calculate the temperature of the protection board at position A and the temperature of the mobile phone USB board at position B according to the calculated resistance value to obtain a test temperature set.
  • the effective temperature refers to the temperature collected by the mobile phone when the NTC resistance is normal. After the mobile phone obtains the test temperature set, it can be judged whether each test temperature in the test temperature set (each test temperature refers to the temperature of the protection board at the position A and the temperature of the mobile phone USB small board at the position B) is greater than the first
  • the preset threshold is less than the second preset threshold. If the test temperature is greater than the first preset threshold and less than the second preset threshold, determining that the test temperature is an effective temperature, and if the test temperature is less than or equal to the first preset threshold, or greater than or equal to the second preset threshold, It is determined that the test temperature is not an effective temperature.
  • first preset threshold and the second preset threshold may be preset in the mobile phone, so that the mobile phone determines, according to the first preset threshold and the second preset threshold, whether each test temperature in the test temperature set is valid. temperature.
  • the mobile phone can determine that the temperature of the protection board at position A is the effective temperature, and the location of the mobile phone USB small board at position B Temperature is not an effective temperature.
  • the mobile phone determines the target neural network model from the set of neural network models according to the position of each of the M effective temperatures corresponding to the test component.
  • the mobile phone may first determine the input variable set according to the position and the first mapping relationship corresponding to each valid temperature in the M effective temperatures, and then according to the input variable set and the second The mapping relationship determines the target neural network model from the neural network model set.
  • the first mapping relationship includes a correspondence between a position of each of the M effective temperatures corresponding to the effective component in the test component and the input variable
  • the second mapping relationship includes a correspondence between the input variable set and the target neural network model.
  • the first mapping relationship and the second mapping relationship may be pre-stored in the mobile phone in the form of a table.
  • Table 2 the correspondence between the location and the input variable in the test component is as shown in Table 3. Enter the correspondence between the variable set and the neural network model.
  • the set of neural network models in the state of charge and the state of discharge are different, before the mobile phone determines the target neural network model from the set of neural network models, it is necessary to first query the charging chip to determine whether the mobile phone is currently in a charging state or The state of discharge is such that the target neural network model is determined from the set of neural network models in the state in which the handset is currently located.
  • the mobile phone may first determine the input according to the effective temperature corresponding to the position A of the protection board.
  • the variable is X 1
  • the mobile phone displays a prompt message and/or initiates a shutdown procedure.
  • the mobile phone can display a prompt message for prompting the user to not estimate the temperature, so that after the user sees the prompt information, the mobile phone is faulty and needs to be repaired to protect the battery core.
  • the phone can also display the prompt message before starting the shutdown process.
  • the phone can also directly start the shutdown process.
  • the mobile phone determines the temperature of the battery cell at the target position C according to the M effective temperature and the target neural network model.
  • the mobile phone determines the temperature of the battery cell at the target position C according to the M effective temperature and the target neural network model, not only the temperature of the cell estimated by the mobile phone due to the abnormal NTC resistance set at the preset position can be avoided.
  • the neural network model can reflect the causal relationship between the temperature of the cell and the temperature of the protection board and the temperature of the USB board of the mobile phone in real time, and thus it is used in the prior art.
  • the compensation algorithm estimates the temperature of the cell compared to the temperature of the cell estimated in the present application. And through practice, the deviation of the cell temperature estimated by the mobile phone according to the effective temperature and the neural network model is at most 3 ° C, and the deviation in most cases is within 1 ° C.
  • the cell can determine that the temperature of the cell at the target position C is 17.9 °C.
  • the mobile phone determines, according to the current state of the mobile phone, whether the temperature of the battery cell at the target position C is greater than a threshold value.
  • the mobile phone since the mobile phone is charging and discharging, it is necessary to take protective measures when determining that the temperature of the battery reaches the threshold to achieve temperature protection of the battery. Moreover, when charging and discharging, the threshold value for judging whether protection measures need to be taken is different, and the protection measures taken are also different. Therefore, after the mobile phone estimates the temperature of the battery cell at the target position C, it can be based on the current location of the mobile phone. The state determines the corresponding threshold value, and determines whether the temperature of the battery cell at the target position C is greater than the corresponding threshold value. If the mobile phone determines that the temperature of the battery cell at the target location C is greater than the corresponding threshold, step 308 may be performed. If the mobile phone determines that the temperature of the cell at the target location C is less than the corresponding threshold, step 302-step 307 may be re-executed to monitor the cell temperature in real time.
  • the mobile phone when the current state of the mobile phone is in a charging state, the mobile phone can determine whether the temperature of the battery cell at the target position C is greater than a threshold value in the charging state. When the current state of the mobile phone is in a discharged state, the mobile phone can determine whether the temperature of the battery cell at the target position C is greater than a threshold value in the discharged state.
  • the threshold values in the charging state and the discharging state may be preset in the mobile phone. Exemplarily, if the threshold value in the charging state is 45 ° C and the threshold value in the discharging state is 65 ° C, then if the current mobile phone is in the charging state, it can be determined whether the temperature of the cell at the target position C is greater than 45. °C, if the current mobile phone is in the discharge state, it can be judged whether the temperature of the battery cell at the target position C is greater than 65 °C.
  • the mobile phone takes corresponding protective measures.
  • the mobile phone when the current state of the mobile phone is in a charging state, the mobile phone can limit the current to lower the cell temperature and achieve temperature protection of the cell.
  • the mobile phone When the current state of the mobile phone is in a discharged state, the mobile phone can start a shutdown procedure to stop the battery discharge, thereby achieving the purpose of lowering the temperature of the battery core, and achieving temperature protection of the battery core.
  • the target location C may also refer to the location of the mobile phone casing.
  • the temperature of the mobile phone casing may be estimated by using the method of estimating temperature provided by the present application.
  • the method for estimating temperature detects the temperature of the component at each of the N locations, and after obtaining the test temperature set, the effective temperature set including the M effective temperatures can be determined from the test temperature set.
  • M is greater than 0 and less than or equal to N
  • the target neural network model is determined from the neural network model set according to the position of each of the M effective temperatures corresponding to the position in the test component, and according to the M effective temperatures and targets
  • the neural network model determines the temperature of the component to be estimated at the target location.
  • the neural network model of causality estimates the temperature of the cell, and therefore the deviation of the temperature of the cell estimated by the method of estimating temperature of the present application is compared with the estimation of the temperature of the cell by the coarse compensation algorithm in the prior art. Smaller.
  • the temperature of the test component according to the abnormality The estimated cell temperature still has a large deviation. Therefore, the accuracy of the estimated cell temperature is further improved by estimating the cell temperature based only on the temperature of the effective test component, that is, the effective temperature.
  • the mobile phone uses the estimated temperature method of the present application to estimate the deviation of the temperature of the battery core is small, and the compensation algorithm using the prior art requires a large safety margin to estimate the temperature of the battery cell.
  • the cell temperature estimated using the method of estimating temperature of the present application does not easily reach the threshold.
  • the mobile phone can display the prompt information and/or start the shutdown program, so that the user can obtain the fault information to perform the maintenance of the device, thereby avoiding the problem that the component to be estimated has a safety hazard due to the inability to estimate the temperature of the component to be estimated.
  • the means for estimating the temperature includes hardware structures and/or software modules for performing the respective functions in order to implement the above functions.
  • the present application can be implemented in a combination of hardware or hardware and computer software in combination with the algorithmic steps of the various examples described in the embodiments disclosed herein. Whether a function is implemented in hardware or computer software to drive hardware depends on the specific application and design constraints of the solution. A person skilled in the art can use different methods to implement the described functions for each particular application, but such implementation should not be considered to be beyond the scope of the present application.
  • the present application may divide the function module by the device for estimating the temperature according to the above method example.
  • each function module may be divided according to each function, or two or more functions may be integrated into one processing module.
  • the above integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the present application is schematic, and is only a logical function division, and may be further divided in actual implementation.
  • FIG. 7 shows a possible composition diagram of the apparatus for estimating temperature referred to in the above and the present application.
  • the apparatus for estimating the temperature may include : acquisition unit 41 and determination unit 42.
  • the acquisition unit 41 is configured to support step 201 of the method for estimating temperature, and step 302 of the method for estimating temperature shown in FIG. 3.
  • the determining unit 42 is configured to support step 203, step 203, and step 204 in the method for estimating the temperature shown in FIG. 2, and step 303, step 304, and step in the method for estimating temperature shown in FIG. 306.
  • the device for estimating the temperature may further include: a display unit 43, an activation unit 44, and an acquisition unit 45.
  • the display unit 43 is configured to support the display of the prompt information described in step 305 of the method for estimating the temperature shown in FIG.
  • the startup unit 44 is configured to support the startup shutdown procedure described in step 305 of the method for estimating the temperature shown in FIG.
  • the obtaining unit 45 is configured to support step 301 in the method of estimating the temperature by the means for estimating the temperature shown in FIG.
  • the apparatus for estimating temperature provided by the present application is for performing the above-described method of estimating the temperature, and thus the same effect as the above-described method of estimating the temperature can be achieved.
  • Fig. 9 shows another possible compositional diagram of the device for estimating the temperature involved in the above embodiment.
  • the device for estimating temperature includes a processing module 51 and a communication module 52.
  • the processing module 51 is configured to control and manage the action of the device for estimating the temperature.
  • the device for supporting the estimated temperature by the processing module 51 performs step 201, step 202, step 203 and step 204 in FIG. 2, steps in FIG. 301, step 302, step 303, step 304, step 305, step 306, step 307, step 308, and/or other processes for the techniques described herein.
  • Communication module 52 is used to support communication of devices that estimate temperature with other network entities.
  • the means for estimating the temperature may further comprise a storage module 53 for storing program codes and data of the means for estimating the temperature.
  • the processing module 51 can be a processor or a controller. It is possible to implement or carry out the various illustrative logical blocks, modules and circuits described in connection with the present disclosure.
  • the processor can also be a combination of computing functions, such as a combination of one or more microprocessors, a combination of a Digital Signal Processor (DSP) and a microprocessor, and the like.
  • the communication module 52 can be a transceiver, a transceiver circuit, a communication interface, or the like.
  • the storage module 53 can be a memory.
  • the disclosed apparatus and method may be implemented in other manners.
  • the device embodiments described above are merely illustrative.
  • the division of the modules or units is only a logical function division.
  • there may be another division manner for example, multiple units or components may be used.
  • the combination may be integrated into another device, or some features may be ignored or not performed.
  • the mutual coupling or direct coupling or communication connection shown or discussed may be an indirect coupling or communication connection through some interface, device or unit, and may be in an electrical, mechanical or other form.
  • the units described as separate components may or may not be physically separated, and the components displayed as units may be one physical unit or multiple physical units, that is, may be located in one place, or may be distributed to multiple different places. . Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of the embodiment.
  • each functional unit in each embodiment of the present application may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit.
  • the above integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
  • the integrated unit if implemented in the form of a software functional unit and sold or used as a standalone product, may be stored in a readable storage medium.
  • the technical solution of the present application or the part that contributes to the prior art or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium.
  • a number of instructions are included to cause a device (which may be a microcontroller, chip, etc.) or a processor to perform all or part of the steps of the methods described in various embodiments of the present application.
  • the foregoing storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard disk, a ROM, a RAM, a magnetic disk, or an optical disk.

Landscapes

  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Secondary Cells (AREA)

Abstract

L'invention concerne un procédé et un appareil pour estimer une température, se rapportant au domaine des communications, et résolvant le problème résidant dans le fait qu'il existe un écart important dans la température de cellule estimée par un dispositif électronique rechargeable. La solution spécifique consiste à : recueillir la température d'un composant de test à chacune de N positions pour obtenir un ensemble de températures de test (201), N étant un nombre entier supérieur ou égal à deux ; déterminer un ensemble de températures effectives à partir de l'ensemble de températures de test, l'ensemble de températures effectives contenant M températures effectives (202), et M étant un nombre entier supérieur ou égal à zéro et inférieur ou égal à N ; lorsque M est supérieur à zéro et inférieur ou égal à N, déterminer un modèle de réseau neuronal cible à partir d'un ensemble de modèles de réseau neuronal en fonction de la position correspondante de chacune des M températures effectives dans le composant de test (203) ; et déterminer la température d'un composant à évaluer à une position cible en fonction des M températures effectives et du modèle de réseau neuronal cible (204). Le procédé est utilisé pour le processus d'estimation de température.
PCT/CN2017/078197 2016-11-24 2017-03-24 Procédé et appareil d'estimation de température WO2018094929A1 (fr)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201780005080.1A CN108474823B (zh) 2016-11-24 2017-03-24 一种估算温度的方法及装置

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201611045628.9 2016-11-24
CN201611045628 2016-11-24

Publications (1)

Publication Number Publication Date
WO2018094929A1 true WO2018094929A1 (fr) 2018-05-31

Family

ID=62195764

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/078197 WO2018094929A1 (fr) 2016-11-24 2017-03-24 Procédé et appareil d'estimation de température

Country Status (2)

Country Link
CN (1) CN108474823B (fr)
WO (1) WO2018094929A1 (fr)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110955580A (zh) * 2019-12-09 2020-04-03 Oppo广东移动通信有限公司 壳体温度的获取方法、装置、存储介质和电子设备
CN113484770A (zh) * 2021-06-10 2021-10-08 广东恒翼能科技有限公司 基于充放电数据在线测算电池内部核心温度的方法及系统

Families Citing this family (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111823952B (zh) * 2020-04-17 2022-07-05 北京嘀嘀无限科技发展有限公司 电芯温度的诊断方法、存储介质和电子设备
CN113422412A (zh) * 2021-07-01 2021-09-21 广州飞傲电子科技有限公司 温度保护方法、装置、终端设备和可读存储介质
CN114520389A (zh) * 2022-02-23 2022-05-20 阳光电源股份有限公司 储能装置内部温度的确定方法及装置
CN117613326B (zh) * 2024-01-23 2024-04-05 新研氢能源科技有限公司 一种基于区域温度的燃料电池控制方法

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102646332A (zh) * 2011-02-21 2012-08-22 日电（中国）有限公司 基于数据融合的交通状态估计装置和方法
CN103967963A (zh) * 2014-05-21 2014-08-06 合肥工业大学 基于神经网络预测的dct湿式离合器温度的测量方法
CN104865534A (zh) * 2015-04-29 2015-08-26 同济大学 一种单体电池内部温度估计方法
CN105468054A (zh) * 2015-12-10 2016-04-06 长江大学 刹车温度监控装置及智能控制方法

Family Cites Families (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4199574B2 (ja) * 2003-03-31 2008-12-17 古河電池株式会社 蓄電池の内部インピーダンス測定方法
FR2876152B1 (fr) * 2004-10-06 2006-12-15 Renault Sas Procede et systeme ameliores d'estimation d'une temperature des gaz d'echappement et moteur a combustion interne equipe d'un tel systeme
CN201307765Y (zh) * 2008-08-30 2009-09-09 深圳华为通信技术有限公司 一种电池保护装置及终端设备
FR2980307B1 (fr) * 2011-09-15 2014-11-07 Renault Sa Methode pour estimer la temperature au coeur d'une cellule de batterie
CN204558611U (zh) * 2015-03-17 2015-08-12 北汽福田汽车股份有限公司 一种用于电池内部温度测试的电池装置
CN104864984B (zh) * 2015-05-21 2017-04-05 青岛大学 基于神经网络的微小反应器温度测量方法
CN204791125U (zh) * 2015-07-21 2015-11-18 桂林电子科技大学 电动汽车动力电池温度预测及散热装置

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102646332A (zh) * 2011-02-21 2012-08-22 日电（中国）有限公司 基于数据融合的交通状态估计装置和方法
CN103967963A (zh) * 2014-05-21 2014-08-06 合肥工业大学 基于神经网络预测的dct湿式离合器温度的测量方法
CN104865534A (zh) * 2015-04-29 2015-08-26 同济大学 一种单体电池内部温度估计方法
CN105468054A (zh) * 2015-12-10 2016-04-06 长江大学 刹车温度监控装置及智能控制方法

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
ZHAO, LIYAN ET AL.: "Sensor system with NTC Thermistor based on Neural Network Compensation", INSTRUMENT TECHNIQUE AND SENSOR, vol. 5, no. 31, 31 May 2008 (2008-05-31) *

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110955580A (zh) * 2019-12-09 2020-04-03 Oppo广东移动通信有限公司 壳体温度的获取方法、装置、存储介质和电子设备
CN110955580B (zh) * 2019-12-09 2023-10-03 Oppo广东移动通信有限公司 壳体温度的获取方法、装置、存储介质和电子设备
CN113484770A (zh) * 2021-06-10 2021-10-08 广东恒翼能科技有限公司 基于充放电数据在线测算电池内部核心温度的方法及系统

Also Published As

Publication number Publication date
CN108474823B (zh) 2022-02-25
CN108474823A (zh) 2018-08-31

Similar Documents

Publication Publication Date Title
WO2018094929A1 (fr) Procédé et appareil d'estimation de température
US11056905B2 (en) Battery charging management method and terminal
US11031788B2 (en) Charging control method for battery based on time and electronic device supporting the same
EP2808652B1 (fr) Dispositif électronique portable avec capteur de température intégré compensée par des donnes d'autre senseurs
EP2793450B1 (fr) Système et procédé permettant de déterminer la précision du capteur d'un dispositif électronique portable
CN104599850B (zh) 一种充电方法及装置
US9562869B2 (en) Portable electronic device
CN108988421B (zh) 一种电池的充电方法、充电电路以及终端
CN110861533B (zh) 电动汽车soh估算方法、装置和存储介质
WO2017096978A1 (fr) Procédé et dispositif de compensation de température pour terminal mobile et terminal mobile
CN104729748B (zh) 用于确定移动设备的环境温度的方法
CN107423197B (zh) 电子设备、温升控制方法、控制装置及存储介质
CN110299737A (zh) 电力管理的方法、装置和电子设备
JP2019095948A (ja) 携帯電子機器、プロセッサ制御方法およびプロセッサ制御プログラム
US11024885B2 (en) Electronic apparatus and control method thereof
WO2017191908A1 (fr) Procédé de calcul d'informations de localisation et dispositif électronique associé
WO2022047767A1 (fr) Procédé et appareil de détection de la puissance d'une batterie et dispositif électronique portable
CN109642827B (zh) 温度推算系统、温度推算方法及记录有温度推算程序的记录媒体
CN109860743B (zh) 一种充电方法及终端设备
WO2014113959A1 (fr) Matériel et logiciel de sonde intégrés
CN211477413U (zh) 可定位的体温检测装置和基于物联网的体温检测监控系统
CN108200290A (zh) 电子装置、跌落损坏的确定方法以及相关产品
KR102472161B1 (ko) 이차 전지 성능 추정 장치 및 방법
CN112539840A (zh) 具有温湿度传感器的便携式热像仪系统及热像检测方法
JP2010538263A (ja) データロガーシステム

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 17874635

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

122 Ep: pct application non-entry in european phase

Ref document number: 17874635

Country of ref document: EP

Kind code of ref document: A1