High-safety wide-temperature-range analog quantity correction method, system, equipment and medium

Abstract

The invention relates to an electromechanical equipment analog quantity acquisition and correction technology, and discloses a high-safety wide-temperature-range analog quantity correction method, system and device and a medium, and the method comprises the steps: obtaining an impact factor related to temperature drift; acquiring analog quantity data corresponding to different excitation values of the analog quantity acquisition interface at each test temperature to obtain a training data set; training the initial BP neural network through the training data set to obtain a trained BP neural network, and storing the correction configuration information corresponding to each analog quantity interface and the trained BP neural network into a nonvolatile storage area; and according to the trained BP neural network read from the nonvolatile storage area and the correction configuration information of each analog quantity interface, analog quantity data acquired by the analog quantity acquisition interface are corrected to obtain final analog quantity data. According to the method, the acquisition error in a wide temperature range can be effectively corrected, the acquisition performance of a product is greatly improved, and the control performance of an aircraft is effectively improved.

Description

Technical Field

[0001] The present invention belongs to the field of airborne computers and relates to a technology for collecting and correcting analog quantities of electromechanical equipment, and in particular to a method, system, device and medium for correcting analog quantities with high safety and a wide temperature range. Background Art

[0002] There are multiple sensors in the aircraft electromechanical system for collecting analog quantities such as temperature, pressure, and speed. Analog quantity acquisition is an important functional component of the aircraft electromechanical integrated system. The acquisition accuracy, data processing speed, and data reliability of its hardware interface will directly affect the control performance indicators of the electromechanical management system. Therefore, the system has increasingly higher requirements for the sensor's acquisition accuracy, acquisition speed, and data stability.

[0003] In recent years, the domestic sensor electronic component manufacturing industry has achieved certain development, but due to process reasons, the consistency of sensor components is poor, and many key components have a certain gap with system requirements in terms of performance, function and reliability. Especially for avionics equipment, the operating temperature requirement is between -55℃ and 125℃, which belongs to the wide temperature range requirement. Under extreme temperature conditions, the performance parameters of some sensor components will drift and fail to meet the performance requirements. Therefore, in actual applications, in order to obtain better acquisition performance indicators and meet low-cost requirements, specific processing algorithms are usually used to correct the analog quantities of the collected airborne equipment. The traditional analog quantity correction method is to make a unified and fixed correction to the collected value. This method cannot correct the temperature drift characteristics of the product analog quantity interface during acquisition. Summary of the invention

[0004] In order to solve the technical problem that when sensor components are used under wide temperature range conditions, the analog quantity acquisition value is corrected by a unified and fixed correction method, and the correction result has low accuracy due to temperature drift, the present invention discloses a high-safety wide temperature range analog quantity correction method, the method comprising the following steps:

[0005] S1. Obtaining influencing factors related to temperature drift according to temperature drift characteristics of interface components, wherein the influencing factors include ambient temperature;

[0006] S2, collecting analog data corresponding to different excitation values ​​of each analog quantity acquisition interface at each test temperature to obtain a training data set;

[0007] S3, training the initial BP neural network with the training data set to obtain a trained BP neural network, and storing the modified configuration information and the trained BP neural network in a non-volatile storage area;

[0008] S4. According to the trained BP neural network read from the non-volatile storage area and the correction configuration information corresponding to the analog quantity interface, the analog quantity data collected by the analog quantity acquisition interface is corrected to obtain the final analog quantity data.

[0009] Further, in step S2, analog data corresponding to different excitation values ​​of each analog quantity acquisition interface at each test temperature is collected to obtain a training data set, including:

[0010] S21, dividing the operating temperature range of each analog quantity acquisition interface into a plurality of temperature segments according to a preset time;

[0011] S22, within each of the temperature segments, dividing the excitation range of each of the analog quantity acquisition interfaces into a plurality of excitation segments according to a preset excitation value;

[0012] S23, collecting the analog value corresponding to each of the excitation segments in each of the temperature segments to obtain a training data set.

[0013] Furthermore, the analog quantity interface includes any one of a voltage signal acquisition interface, a current signal acquisition interface, a resistance signal acquisition interface and a frequency signal acquisition interface.

[0014] Furthermore, the initial BP neural network includes an input layer, multiple hidden layers and an output layer, the input layer inputs the test temperature and the analog data corresponding to each excitation value at the test temperature, the hidden layer uses the ReLU activation function, and the output layer uses a linear activation function to output the corrected analog data.

[0015] Furthermore, in step S3, the initial BP neural network is trained by the training data set to obtain a trained BP neural network, including:

[0016] S31, adopting a stochastic gradient descent algorithm, taking the minimum MMSE loss function as a constraint, training the initial BP neural network through the training data set, so as to obtain a trained BP neural network, and encapsulating the trained BP neural network;

[0017] S32, storing the packaged trained BP neural network and the correction configuration information of each analog interface in a non-volatile storage area, wherein the correction configuration information includes temperature drift correction and non-temperature drift correction.

[0018] Further, in step S4, according to reading the trained BP neural network and the correction configuration information corresponding to the analog interface from the non-volatile storage area, the analog data collected by the analog acquisition interface is corrected to obtain the final analog data, including:

[0019] S41, reading the correction configuration information corresponding to the analog interface from the non-volatile storage area, and verifying the correction configuration information;

[0020] S42, when the verification passes and the correction configuration information read is temperature drift correction, the trained BP neural network is used to correct the analog data collected by the analog acquisition interface to obtain the final analog data;

[0021] S43, when the verification fails, or when the verification passes but the correction configuration information read is that the temperature drift is not corrected, the analog data collected by the analog acquisition interface is used as the final analog data.

[0022] The embodiment of the present invention further provides a high-safety and wide-temperature range analog quantity correction system, which includes an influencing factor acquisition module, a data acquisition module, a network training module and an analog quantity correction module.

[0023] The influencing factor acquisition module is used to acquire influencing factors related to temperature drift according to the temperature drift characteristics of the interface components, and the influencing factors include the ambient temperature;

[0024] The data acquisition module is used to collect analog data corresponding to different excitation values ​​of each analog acquisition interface at each test temperature to obtain a training data set;

[0025] The network training module is used to train the initial BP neural network through the training data set to obtain the trained BP neural network, and store the modified configuration information and the trained BP neural network in the non-volatile storage area;

[0026] The analog quantity correction module is used to correct the analog quantity data collected by the analog quantity acquisition interface to obtain the final analog quantity data according to the trained BP neural network and the correction configuration information corresponding to the analog quantity interface read from the non-volatile storage area.

[0027] An embodiment of the present invention also provides a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned high-safety and wide-temperature range analog correction methods when executing the computer program, so as to solve the technical problem that when sensor components are used under wide temperature range conditions, the analog acquisition values ​​are corrected by a unified and fixed correction method, and the correction results have low accuracy due to temperature drift.

[0028] An embodiment of the present invention also provides a computer-readable storage medium, which stores a computer program for executing any of the above-mentioned high-safety wide-temperature range analog correction methods, so as to solve the technical problem of low accuracy of correction results due to temperature drift when analog acquisition values ​​are corrected through a unified and fixed correction method when sensor components are used under wide temperature range conditions.

[0029] Compared with the prior art, at least one of the above-mentioned technical solutions adopted in the embodiments of this specification can achieve at least the following beneficial effects: the method of the present invention can effectively correct the acquisition errors of various analog interfaces in the product under a wide temperature range, greatly improving the acquisition performance of the product, and effectively improving the aircraft control performance without increasing the design cost. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0031] Figure 1 It is a flow chart of the analog quantity correction method with high safety and wide temperature range disclosed in an embodiment of the present invention;

[0032] Figure 2 A schematic diagram of a BP neural network disclosed in an embodiment of the present invention;

[0033] Figure 3 The writing process of the modified configuration information in the non-volatile storage area disclosed in the embodiment of the present invention;

[0034] Figure 4 A flow chart of correcting analog data collected by an analog quantity acquisition interface using a trained BP neural network disclosed in an embodiment of the present invention;

[0035] Figure 5 This is an architecture diagram of a high-safety, wide-temperature range analog correction system disclosed in an embodiment of the present invention;

[0036] Among them, 501 is an impact factor acquisition module; 502 is a data acquisition module; 503 is a network training module / 504 is an analog quantity correction module. DETAILED DESCRIPTION

[0037] The embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0038] The following describes the implementation methods of the present application through specific specific examples, and those skilled in the art can easily understand other advantages and effects of the present application from the content disclosed in this specification. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. The present application can also be implemented or applied through other different specific implementation methods, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present application. It should be noted that the following embodiments and the features of the embodiments can be combined with each other in the absence of conflict. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without making creative work belong to the scope of protection of the present application.

[0039] The embodiment of the present invention discloses a high-safety and wide-temperature range analog correction method, Figure 1 As shown, the method comprises the following steps:

[0040] S1. Obtaining influencing factors related to temperature drift according to temperature drift characteristics of interface components, wherein the influencing factors include ambient temperature;

[0041] S2, collecting analog data corresponding to different excitation values ​​of each analog quantity acquisition interface at each test temperature to obtain a training data set;

[0042] S3, training the initial BP neural network with the training data set to obtain a trained BP neural network, and storing the modified configuration information and the trained BP neural network in a non-volatile storage area;

[0043] S4. According to the trained BP neural network read from the non-volatile storage area and the correction configuration information corresponding to the analog quantity interface, the analog quantity data collected by the analog quantity acquisition interface is corrected to obtain the final analog quantity data.

[0044] Furthermore, the analog quantity interface includes any one of a voltage signal acquisition interface, a current signal acquisition interface, a resistance signal acquisition interface and a frequency signal acquisition interface. Through experiments, it is found that there are errors in the acquisition of each type of analog quantity interface, and the errors are different at different temperatures. Therefore, in step S1, the dynamic acquisition error of the interface can be analyzed according to the temperature drift characteristics of the components. The correction target is the input excitation value, and the influencing factor that needs to be corrected is the temperature. For example: The correction formula for the resistance acquisition interface of a certain product can be expressed as:

[0045] g(x,T)=x+f(x,T);

[0046] Among them, x is the actual collected value, T is the current ambient temperature, f(x,T) is the correction parameter, and g(x,T) is the corrected collected value. The correction result of the interface collected value will be obtained through the algorithm later.

[0047] Further, in step S2, analog data corresponding to different excitation values ​​of each analog quantity acquisition interface at each test temperature is collected to obtain a training data set, including:

[0048] S21, dividing the operating temperature range of each analog quantity acquisition interface into a plurality of temperature segments according to a preset time;

[0049] S22, within each of the temperature segments, dividing the excitation range of each of the analog quantity acquisition interfaces into a plurality of excitation segments according to a preset excitation value;

[0050] S23, collecting the analog value corresponding to each of the excitation segments in each of the temperature segments to obtain a training data set.

[0051] In the specific implementation, it is necessary to use a training data set to select the algorithm for analog correction. The method for obtaining the training data set is as follows: the ambient temperature of the product (that is, the test temperature) such as -55℃~125℃ can be segmented, for example, every 2℃ can be divided into a segment. The excitation can also be set in segments within each temperature range. For example: for the PT1000 resistance acquisition interface (assuming that its resistance acquisition range is 0-5000Ω), it can be divided into a segment every 10Ω, thereby obtaining a set of acquisition data under each ambient temperature segment, and each acquisition value and excitation value are expressed as (x,y). Among them, x=[x1,x2…x n ] is the actual collected value under the current ambient temperature T, y=[y1,y2…y n ] are the n excitation values ​​corresponding to the current ambient temperature T. Then, for different ambient temperatures and different excitation values, different (x, y) can be obtained.

[0052] Further, see Figure 2 As shown, the initial BP neural network includes an input layer, multiple hidden layers (the specific number of layers needs to be determined according to the training results) and an output layer. The input layer inputs the test temperature and the analog data corresponding to each excitation value under the test temperature. The hidden layer uses the ReLU activation function, and the output layer uses the linear activation function to output the corrected analog data. Figure 2 As shown in the figure, the input information of the BP neural network is the analog interface at the current ambient temperature and the analog value collected at that temperature [T, x1, ... x n ], the network output information is the corrected analog acquisition value The number of hidden layers can be adjusted during the training process. For example, for the PT1000 resistor, the hidden layer uses the ReLU activation function and the output layer uses the linear activation function. The ReLU function sets the output value less than 0 to 0 to ensure that the output value is a positive number. This function has the effect of reducing the computational complexity and avoiding the disappearance of the gradient.

[0053] Further, according to theoretical analysis, the acquisition value of the interface is related to the ambient temperature and the excitation, but it is difficult to obtain an accurate mapping relationship. Therefore, in order to correct the acquisition value of the interface, a BP neural network with strong nonlinear fitting ability can be used for learning and training. In step S3, the initial BP neural network is trained by the training data set to obtain a trained BP neural network, including:

[0054] S31, adopting a stochastic gradient descent algorithm, taking the minimum MMSE loss function as a constraint, training the initial BP neural network through the training data set, so as to obtain a trained BP neural network, and encapsulating the trained BP neural network;

[0055] S32, storing the packaged trained BP neural network and the correction configuration information of each analog interface in a non-volatile storage area, wherein the correction configuration information includes temperature drift correction and non-temperature drift correction.

[0056] When training the initial BP neural network, the network weights are trained using the stochastic gradient descent algorithm. This algorithm does not need to use all the data in the training data set when optimizing the network, and has the advantage of fast calculation speed. The goal of network training is to minimize the mean square error. The loss function can use the MMSE (minimum mean square error) function, which is expressed as:

[0057]

[0058] Among them, w is the weight matrix of BP neural network, b is the bias matrix of BP neural network, y is the training label vector, is the output vector of the BP neural network. During the network training process, the difference between the actual output of the BP neural network and the training label is the error. The error information output is transmitted backward from the output layer layer by layer along the original path. By gradually selecting the weights of neurons in each layer, the actual output of the BP neural network will become closer and closer to the expected output, so that the error will become smaller and smaller.

[0059] After the BP neural network is trained, the trained BP neural network is packaged so that the device can use the network to correct the analog acquisition value. The specific implementation process is: the parameters of the trained BP neural network are saved and packaged. In the embedded software coding stage, the packaged BP neural network is called to configure the BP neural network into the product. Whether to use the network for parameter correction is determined by the configuration information. In other words, in the software design stage, coders only need to use the packaged BP neural network like using ordinary library functions.

[0060] Whether to use the trained BP neural network to correct the temperature drift of analog data is configurable, and the correction configuration information is also read from the non-volatile storage area. Specifically, before the product is officially put into use, the product designer should ensure that the correction configuration information is written to the non-volatile storage area. For the correction configuration information writing, see Figure 3 As shown. For example, when the correction configuration information written is "0X55", it means "using network correction temperature drift", and the others mean "not using network correction temperature drift". At the same time, in order to ensure that there is no other data in the non-volatile storage area to be written, the selected non-volatile storage area can also be cleared before the data is written, or a dedicated area can be allocated for the correction configuration information. After the correction configuration information of various analog interfaces is written, a checksum should be added to the data area and written to the non-volatile storage area. The checksum calculation method is: sum the data to be checked by byte, and perform a complement operation on the result. After writing is completed, it is necessary to read the written correction configuration information from the non-volatile storage area immediately, and verify whether the writing is successful in the above way. After the verification is successful, "Parameter configuration successful" is printed; otherwise, "Parameter configuration failed" is printed and the current non-volatile storage area is cleared.

[0061] Further, in step S4, according to reading the trained BP neural network and the correction configuration information corresponding to the analog interface from the non-volatile storage area, the analog data collected by the analog acquisition interface is corrected to obtain the final analog data, including:

[0062] S41, reading the correction configuration information corresponding to the analog interface from the non-volatile storage area, and verifying the correction configuration information;

[0063] S42, when the verification passes and the correction configuration information read is temperature drift correction, the trained BP neural network is used to correct the analog data collected by the analog acquisition interface to obtain the final analog data;

[0064] S43, when the verification fails, or when the verification passes but the correction configuration information read is that the temperature drift is not corrected, the analog data collected by the analog acquisition interface is used as the final analog data.

[0065] Specifically, see Figure 4 As shown in the figure, first, after the analog interface collects the raw data, it needs to read the configurable parameters and calculate the checksum from the non-volatile storage area. After the check is successful, if the correction configuration information read is "0X55", the network correction temperature drift is used; if the correction configuration information is other, the network correction temperature drift is not used. If the check is unsuccessful, the original collection result is reported directly without using the BP neural network for correction. At this point, the analog interface collection and parameter adjustment is completed.

[0066] The method and scheme of the present invention can effectively correct the acquisition errors of various analog interfaces in the product under a wide temperature range, greatly improving the acquisition performance of the product and effectively improving the aircraft control performance without increasing the design cost.

[0067] Based on the same inventive concept, an analog quantity correction system with high safety and wide temperature range is also provided in the embodiments of the present invention, as described in the following embodiments. Since the principle of solving the problem by the analog quantity correction system with high safety and wide temperature range is similar to that of the analog quantity correction method with high safety and wide temperature range, the implementation of the analog quantity correction system with high safety and wide temperature range can refer to the implementation of the analog quantity correction method with high safety and wide temperature range, and the repeated parts will not be repeated. As used below, the term "unit" or "module" can be a combination of software and / or hardware that implements predetermined functions. Although the device described in the following embodiments is preferably implemented in software, the implementation of hardware, or a combination of software and hardware, is also possible and conceived.

[0068] Figure 5 is a structural block diagram of a high-safety, wide-temperature range analog correction system disclosed in an embodiment of the present invention, such as Figure 5 As shown, it includes an influencing factor acquisition module 501, a data acquisition module 502, a network training module 503 and an analog quantity correction module 504. The structure is described below.

[0069] The influencing factor acquisition module 501 is used to acquire influencing factors related to temperature drift according to the temperature drift characteristics of the interface components, and the influencing factors include the ambient temperature;

[0070] The data acquisition module 502 is used to collect analog data corresponding to different excitation values ​​of each analog acquisition interface at each test temperature to obtain a training data set;

[0071] The network training module 503 is used to train the initial BP neural network through the training data set to obtain the trained BP neural network, and store the modified configuration information and the trained BP neural network in the non-volatile storage area;

[0072] The analog quantity correction module 504 is used to correct the analog quantity data collected by the analog quantity acquisition interface to obtain the final analog quantity data according to the trained BP neural network and the correction configuration information corresponding to the analog quantity interface read from the non-volatile storage area.

[0073] In this embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, any of the above-mentioned high-safety and wide-temperature range analog quantity correction methods is implemented.

[0074] Specifically, the computer device may be a computer terminal, a server or a similar computing device.

[0075] In this embodiment, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores a computer program for executing any of the above-mentioned high-safety wide-temperature range analog quantity correction methods.

[0076] Specifically, computer-readable storage media include permanent and non-permanent, removable and non-removable media that can be used to store information by any method or technology. Information can be computer-readable instructions, data structures, program modules or other data. Examples of computer-readable storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer-readable storage media does not include temporary computer-readable media (transitory media), such as modulated data signals and carrier waves.

[0077] Obviously, those skilled in the art should understand that the modules or steps of the above-mentioned embodiments of the present invention can be implemented by a general computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and optionally, they can be implemented by a program code executable by a computing device, so that they can be stored in a storage device and executed by the computing device, and in some cases, the steps shown or described can be executed in a different order from that here, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. In this way, the embodiments of the present invention are not limited to any specific combination of hardware and software.

[0078] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the embodiments of the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A high-safety, wide-temperature range analog correction method, characterized in that: include: According to the temperature drift characteristics of the interface components, an influencing factor related to the temperature drift is obtained, wherein the influencing factor includes the ambient temperature; Collect analog data corresponding to different excitation values ​​of each analog quantity acquisition interface at each test temperature to obtain a training data set; The initial BP neural network is trained by the training data set to obtain a trained BP neural network, and the modified configuration information and the trained BP neural network are stored in a non-volatile storage area; According to the trained BP neural network read from the non-volatile storage area and the correction configuration information corresponding to the analog quantity interface, the analog quantity data collected by the analog quantity acquisition interface is corrected to obtain the final analog quantity data.

2. The analog correction method with high safety and wide temperature range according to claim 1 is characterized in that: Collect analog data corresponding to different excitation values ​​of each analog acquisition interface at each test temperature to obtain a training data set, including: According to a preset time, the operating temperature range of each analog quantity acquisition interface is divided into a plurality of temperature sections; In each of the temperature sections, the excitation range of each of the analog quantity acquisition interfaces is divided into a plurality of excitation sections according to a preset excitation value; The analog value corresponding to each of the excitation segments in each of the temperature segments is collected to obtain a training data set.

3. The analog correction method with high safety and wide temperature range according to claim 1 is characterized in that: The analog quantity interface includes any one of a voltage signal acquisition interface, a current signal acquisition interface, a resistance signal acquisition interface and a frequency signal acquisition interface.

4. The analog correction method with high safety and wide temperature range according to claim 1 is characterized in that: The initial BP neural network includes an input layer, multiple hidden layers and an output layer. The input layer inputs the test temperature and the analog data corresponding to each excitation value under the test temperature. The hidden layer uses the ReLU activation function, and the output layer uses a linear activation function to output the corrected analog data.

5. The analog correction method with high safety and wide temperature range according to claim 1 or 4, characterized in that: The initial BP neural network is trained by the training data set to obtain a trained BP neural network, including: Using a stochastic gradient descent algorithm and taking the minimum MMSE loss function as a constraint, the initial BP neural network is trained through the training data set to obtain a trained BP neural network, and the trained BP neural network is encapsulated; The packaged trained BP neural network and the correction configuration information of each analog quantity interface are stored in a non-volatile storage area, wherein the correction configuration information includes temperature drift correction and non-temperature drift correction.

6. The analog correction method with high safety and wide temperature range according to claim 1, characterized in that: According to the trained BP neural network read from the non-volatile storage area and the correction configuration information corresponding to the analog quantity interface, the analog quantity data collected by the analog quantity acquisition interface is corrected to obtain the final analog quantity data, including: Read the correction configuration information corresponding to the analog interface from the non-volatile storage area, and verify the correction configuration information; When the verification is passed and the correction configuration information read is temperature drift correction, the trained BP neural network is used to correct the analog data collected by the analog acquisition interface to obtain the final analog data; If the verification fails, or if the verification passes but the correction configuration information read is that the temperature drift is not corrected, the analog data collected by the analog acquisition interface is used as the final analog data.

7. A high-safety, wide-temperature range analog correction system, characterized in that: include: An influence factor acquisition module, the influence factor acquisition module is used to obtain an influence factor related to temperature drift according to the temperature drift characteristics of the interface components, the influence factor including the ambient temperature; A data acquisition module, the data acquisition module is used to collect analog data corresponding to different excitation values ​​of each analog acquisition interface at each test temperature to obtain a training data set; A network training module, the network training module is used to train the initial BP neural network through the training data set to obtain the trained BP neural network, and store the modified configuration information and the trained BP neural network in a non-volatile storage area; The analog quantity correction module is used to correct the analog quantity data collected by the analog quantity acquisition interface to obtain the final analog quantity data based on the trained BP neural network read from the non-volatile storage area and the correction configuration information corresponding to the analog quantity interface.

8. A computer device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the analog quantity correction method with high safety and wide temperature range described in any one of claims 1 to 6 is implemented.

9. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program for executing the analog correction method for a high safety and wide temperature range according to any one of claims 1 to 6.

Images