Error monitoring method and system adaptive to one-ten-thousandth precision balance

Abstract

The invention relates to an error monitoring method and system adaptive to a one-ten-thousandth-precision balance, and belongs to the technical field of error monitoring. The method comprises the following steps: acquiring a multi-modal balance sensor signal, and obtaining a multi-modal balance environment parameter matrix through space-time alignment verification according to the multi-modal balance sensor signal; obtaining balance dynamic tensor coupling information through a physical constraint tensor network according to the multi-modal balance environment parameter matrix; obtaining a balance dynamic error interval through a multi-field coupling equation according to the balance dynamic tensor coupling information; according to the balance dynamic error interval, balance error correction information is obtained through multi-mode environment interference degree analysis, a balance error correction visual graph is output according to the balance error correction information, and dynamic probability evaluation of the balance error interval and balance error correction information visualization are achieved.

Description

Technical Field

[0001] The present invention belongs to the technical field of error monitoring, and particularly relates to an error monitoring method and system adapted to a balance with a precision of one ten-thousandth. Background Art

[0002] As a high-precision weighing tool, a balance with a precision of one ten-thousandth is widely used in fields such as drug research and development, precious metal detection, and precision chemical experiments. The reliability of its measurement results directly affects the validity of experimental data. The balance with a precision of one ten-thousandth has extremely high measurement precision, and external vibrations, airflows, and humidity will all affect it.

[0003] In order to reduce external interference and make the measurement value of the balance more accurate, the prior art reduces interference through physical isolation means, and increases the inertial mass of the system by increasing the mass of the operating table and adding shock-absorbing structures, thereby reducing external interference. However, it lacks intuitive feedback and error correction functions, making it difficult to determine whether the weighing result of the balance is accurate or the error range. In addition, the prior art lacks the ability to quantitatively analyze the coupling effect of multiple interferences and is difficult to predict the comprehensive influence weight on the final weighing value. At the same time, the prior art lacks a dynamic error compensation mechanism. When the environmental interference exceeds the bearing threshold of the vibration isolation system, the balance can only prompt instability through numerical fluctuations, but cannot automatically correct the deviation or calibrate the error confidence interval, forcing experimental personnel to repeatedly perform no-load calibration and sample retesting, seriously reducing the detection efficiency.

[0004] Therefore, there is an urgent need to develop an error monitoring method and system adapted to a balance with a precision of one ten-thousandth to break through the bottleneck of high-precision weighing technology. Summary of the Invention

[0005] To solve the above problems existing in the prior art, the present invention proposes an error monitoring method and system adapted to a balance with a precision of one ten-thousandth.

[0006] The object of the present invention can be achieved by the following technical solutions: An error monitoring method adapted to a balance with a precision of one ten-thousandth, comprising: S1: Obtain multi-modal balance sensor signals, and obtain a multi-modal balance environmental parameter matrix through spatio-temporal alignment verification according to the multi-modal balance sensor signals; S2: Obtain balance dynamic tensor coupling information through a physical constraint tensor network according to the multi-modal balance environmental parameter matrix; S3: Obtain a balance dynamic error range through a multi-field coupling equation according to the balance dynamic tensor coupling information; S4: Obtain balance error correction information through multi-modal environmental interference degree analysis according to the balance dynamic error range, and output a balance error correction visual diagram according to the balance error correction information.

[0007] Preferably, the process of constructing the multi-modal balance environmental parameter matrix in step S1 specifically includes: S101: Obtain the multi-modal balance sensor time synchronization signal through time deviation compensation according to the multi-modal balance sensor signal; S102: Obtain the multi-modal balance environmental parameter matrix through chi-square anomaly detection according to the multi-modal balance sensor time synchronization signal.

[0008] Preferably, the acquisition of the balance dynamic tensor coupling information in step S2 specifically includes: S201: The balance dynamic tensor coupling information includes a balance dynamic weight tensor and a balance interference coupling coefficient matrix; S202: Obtain the balance dynamic weight tensor through physical constraint tensor network training according to the multi-modal balance environmental parameter matrix; S203: Obtain the balance interference coupling coefficient matrix through sliding window covariance calculation according to the balance dynamic weight tensor and the multi-modal balance environmental parameter matrix.

[0009] Preferably, the structure of the physical constraint tensor network in step S202 specifically includes: S202-1: The physical constraint tensor network includes an input layer, a hidden layer, and an output layer. The input layer receives the multi-modal balance environmental parameter matrix. The hidden layer extracts the balance multi-field coupling features through a third-order tensor convolution kernel, and updates the balance dynamic weight tensor according to the balance multi-field coupling features through an adaptive moment estimation optimizer; S202-2: The mathematical expression of the loss function of the physical constraint tensor network is: , where L is the physical constraint tensor network loss term, m is the physical constraint weight coefficient, S T is the temperature field Laplacian operator, k is the thermal diffusivity, is the rate of change of temperature with respect to time, ||.|| F is the Frobenius norm of the multi-modal balance environmental parameter matrix.

[0010] Preferably, the calculation process of the balance dynamic error interval in step S3 includes: S301: Obtain the balance total error standard deviation through a multi-field coupling equation according to the balance dynamic tensor coupling information; S302: Obtain the balance dynamic error interval through confidence interval dynamic boundary calculation according to the balance total error standard deviation.

[0011] Preferably, the mathematical expression of the multi-field coupling equation in step S301 is: , where H is the standard deviation of the total balance error, W i is the weight of the i-th environmental parameter, E i is the value of the i-th environmental parameter, P ij is the coupling coefficient between the i-th environmental parameter and the j-th environmental parameter, and n is the number of environmental parameters.

[0012] Preferably, the generation process of the balance error correction information in step S4 specifically includes: S401: Obtain environmental interference error information through multi-modal environmental interference degree analysis according to the balance dynamic error range. The environmental interference error information includes an environmental interference error coefficient and an environmental stability index; S402: Preset an error correction control rule library, and generate balance error correction information through the error correction control rule library according to the environmental interference error information.

[0013] An error monitoring system adapted to a ten-thousandth precision balance, applied to the above error monitoring method, includes a multi-modal balance environmental parameter matrix acquisition module, a balance dynamic tensor coupling module, a balance dynamic error range calculation module, and a balance error correction visualization module; The multi-modal balance environmental parameter matrix acquisition module is used to acquire multi-modal balance sensor signals and obtain a multi-modal balance environmental parameter matrix through spatio-temporal alignment verification; The balance dynamic tensor coupling module is used to obtain balance dynamic tensor coupling information through a physical constraint tensor network according to the multi-modal balance environmental parameter matrix; The balance dynamic error range calculation module is used to obtain a balance dynamic error range through a multi-field coupling equation according to the balance dynamic tensor coupling information; The balance error correction visualization module is used to obtain balance error correction information through multi-modal environmental interference degree analysis according to the balance dynamic error range and output a balance error correction visualization diagram.

[0014] An electronic device includes a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the computer program, the above error monitoring method is implemented.

[0015] A storage medium containing computer-executable instructions, where the computer-executable instructions are used to execute the above error monitoring method when executed by a computer processor.

[0016] The beneficial effects of the present invention are: (1)By acquiring multi-modal balance sensor signals and obtaining a multi-modal balance environment parameter matrix through spatio-temporal alignment verification, the problem of inconsistent spatio-temporal benchmarks for multi-source sensor signals is solved, the fusion error caused by sampling frequency differences and sensor layout heterogeneity is eliminated, and the data alignment accuracy is improved.

[0017] (2)By using a physical constraint tensor network to obtain balance dynamic tensor coupling information, which combines deep learning and physical constraints, the generalization ability of the model is improved compared with pure data-driven models.

[0018] (3)By using a multi-field coupling equation to obtain the balance dynamic error range, dynamic error quantification modeling is realized. By constructing a simulation model with the multi-field coupling equation, the influence of composite environmental factors such as vibration interference, temperature drift, and air flow disturbance on the measurement accuracy can be calculated in real time, and the dynamic probability assessment of the error range can be realized.

[0019] (4)By analyzing the multi-modal environmental interference degree, the balance error correction information is obtained and the balance error correction visualization diagram is output. The error correction information is visually feedback through visualization, making the complex environment-error coupling relationship concrete. Description of the Drawings

[0020] For the convenience of those skilled in the art to understand, the present invention will be further described below in conjunction with the drawings.

[0021] Figure 1 It is a schematic flow chart of an error monitoring method for a balance adapted to a ten-thousandth precision balance according to the present invention. Detailed Embodiments

[0022] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following will describe in detail the specific embodiments, structures, features, and effects of the present invention in conjunction with the drawings and preferred embodiments.

[0023] Please refer to Figure 1 , an error monitoring method for a balance adapted to a ten-thousandth precision balance, including: S1: Acquire multi-modal balance sensor signals, and obtain a multi-modal balance environment parameter matrix through spatio-temporal alignment verification according to the multi-modal balance sensor signals; S2: Obtain balance dynamic tensor coupling information through a physical constraint tensor network according to the multi-modal balance environment parameter matrix; S3: Obtain the balance dynamic error range through a multi-field coupling equation according to the balance dynamic tensor coupling information; S4: Obtain balance error correction information through multi-modal environmental interference degree analysis according to the balance dynamic error range, and output a balance error correction visualization diagram according to the balance error correction information.

[0024] In this embodiment, the obtaining of the multi-modal balance sensor signal and the obtaining of the multi-modal balance environment parameter matrix through spatio-temporal alignment verification based on the multi-modal balance sensor signal are specifically implemented through the following steps: S101: The multi-modal balance sensor signal includes external micro-vibration data, external air flow vector data, and external humidity data; S101-1: Obtain external micro-vibration data through a micro-vibration sensor. One set of the micro-vibration sensors is deployed in each of the four quadrants of the balance base, and two sets are deployed on the core load-bearing beam, for a total of six sets of sensors; S101-2: Obtain external air flow vector data through a laser. The laser generates an orthogonal grating and obtains the external air flow vector data through Doppler frequency shift detection; The mathematical expression of the Doppler frequency shift detection is: , where V air is the external air flow vector data, Δf is the Doppler frequency shift amount, α is the laser wavelength, and β is the laser incident angle.

[0025] S101-3: Obtain external humidity data through a nanopore humidity sensor. The structure of the nanopore humidity sensor is a graphene nanopore array.

[0026] S102: Obtain a multi-modal balance sensor time synchronization signal through time deviation compensation based on the multi-modal balance sensor signal; S103: Obtain a multi-modal balance environment parameter matrix through chi-square anomaly detection based on the multi-modal balance sensor time synchronization signal.

[0027] In this embodiment, the obtaining of the balance dynamic tensor coupling information through a physical constraint tensor network based on the multi-modal balance environment parameter matrix is specifically implemented through the following steps: S201: The balance dynamic tensor coupling information includes a balance dynamic weight tensor and a balance interference coupling coefficient matrix; S202: Train a balance dynamic weight tensor through a physical constraint tensor network based on the multi-modal balance environment parameter matrix; S202-1: The physical constraint tensor network includes an input layer, a hidden layer, and an output layer. The input layer receives the multi-modal balance environment parameter matrix. The hidden layer extracts balance multi-field coupling features through a third-order tensor convolution kernel, and updates the balance dynamic weight tensor based on the balance multi-field coupling features through an adaptive moment estimation optimizer; S202-2: The mathematical expression of the loss function of the physical constraint tensor network is: , Among them, L is the physical constraint tensor network loss term, m is the physical constraint weight coefficient, and S T is the Laplacian operator of the temperature field, k is the thermal diffusivity, is the rate of change of temperature with respect to time, and ||.|| F is the Frobenius norm of the multi-modal balance environmental parameter matrix.

[0028] S203: Calculate the balance interference coupling coefficient matrix through the sliding window covariance based on the balance dynamic weight tensor and the multi-modal balance environmental parameter matrix.

[0029] The mathematical expression of the balance interference coupling coefficient matrix is: , where P ij is the coupling coefficient between the i-th environmental parameter and the j-th environmental parameter, Cov(E i , E j ) is the covariance between the i-th environmental parameter and the j-th environmental parameter, var(E i ) is the standard deviation of the i-th environmental parameter, and var(E j ) is the standard deviation of the j-th environmental parameter.

[0030] In this embodiment, the specific implementation of obtaining the balance dynamic error range through the multi-field coupling equation based on the balance dynamic tensor coupling information is as follows: S301: Obtain the overall balance error standard deviation through the multi-field coupling equation based on the balance dynamic tensor coupling information; The mathematical expression of the multi-field coupling equation is: , where H is the overall balance error standard deviation, W i is the weight of the i-th environmental parameter, E i is the value of the i-th environmental parameter, P ij is the coupling coefficient between the i-th environmental parameter and the j-th environmental parameter, and n is the number of environmental parameters; S302: Calculate the balance dynamic error range through the dynamic boundary of the confidence interval based on the overall balance error standard deviation.

[0031] The mathematical expression of the dynamic boundary of the confidence interval is: , where Z(t) is the half-width of the balance error confidence interval at time t, z is the Z value corresponding to the preset confidence level, and ||T|| is the temperature gradient norm.

[0032] In this embodiment, the specific implementation of obtaining the balance error correction information through the multi-modal environmental interference degree analysis based on the balance dynamic error range is as follows: S401: Obtain environmental interference error information through multi-modal environmental interference degree analysis based on the balance dynamic error range. The environmental interference error information includes an environmental interference error coefficient and an environmental stability index; S401-1: The mathematical expression of the environmental interference error coefficient is: , , , where, is the environmental interference error coefficient, is the single environmental interference error factor, is the multi-environmental interference coupling error factor, W k is the weight of the k-th environmental parameter, E k is the value of the k-th environmental parameter.

[0033] S401-2: The mathematical expression of the environmental stability index is: , where, S(t) is the environmental stability index at time t, W i is the weight of the i-th environmental parameter, E i is the value of the i-th environmental parameter, E i,max is the maximum allowable value of the i-th environmental parameter.

[0034] S402: Preset an error correction control rule library, and generate balance error correction information through the error correction control rule library based on the environmental interference error information.

[0035] An error monitoring system adapted to a ten-thousandth precision balance includes a multi-modal balance environmental parameter matrix acquisition module, a balance dynamic tensor coupling module, a balance dynamic error range calculation module, and a balance error correction visualization module; The multi-modal balance environmental parameter matrix acquisition module is used to acquire multi-modal balance sensor signals and obtain a multi-modal balance environmental parameter matrix through spatio-temporal alignment verification; The balance dynamic tensor coupling module is used to obtain balance dynamic tensor coupling information through a physical constraint tensor network based on the multi-modal balance environmental parameter matrix; The balance dynamic error range calculation module is used to obtain a balance dynamic error range through a multi-field coupling equation based on the balance dynamic tensor coupling information; The balance error correction visualization module is used to obtain balance error correction information through multi-modal environmental interference degree analysis based on the balance dynamic error range and output a balance error correction visualization diagram.

[0036] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can, for example, but is not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples (non-exhaustive list) of the computer-readable storage medium include: an electrical connection having one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, the computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0037] The computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries the computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0038] The program code embodied on the computer-readable medium can be transmitted by any suitable medium, including but not limited to wireless, wire, optical fiber cable, RF, etc., or any suitable combination of the foregoing. The computer program code for performing the operations of the present invention can be written in one or more programming languages or combinations thereof, including object-oriented programming languages such as Java, Smalltalk, C++, and also including conventional procedural programming languages such as the "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, executed as a stand-alone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or, can be connected to an external computer (for example, by using an Internet service provider to connect through the Internet).

[0039] As described above, the above are only the preferred embodiments of the present invention, and there is no limitation in any form to the present invention. Although the present invention has been disclosed as above with the preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to the equivalent embodiments of equivalent changes within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any simple modification, equivalent change and modification made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. An error monitoring method for adapting to a balance with a precision of one ten-thousandth, characterized in that, Including: S1: Obtain multi-modal balance sensor signals, and obtain a multi-modal balance environment parameter matrix through spatio-temporal alignment verification based on the multi-modal balance sensor signals; S2: Obtain balance dynamic tensor coupling information through a physical constraint tensor network based on the multi-modal balance environment parameter matrix; S3: Obtain a balance dynamic error range through a multi-field coupling equation based on the balance dynamic tensor coupling information; S4: Obtain balance error correction information through multi-modal environmental interference degree analysis based on the balance dynamic error range, and output a balance error correction visualization diagram according to the balance error correction information.

2. The error monitoring method according to claim 1, wherein The construction process of the multi-modal balance environment parameter matrix in step S1 specifically includes: S101: Obtain a multi-modal balance sensor time synchronization signal through time deviation compensation based on the multi-modal balance sensor signals; S102: Obtain a multi-modal balance environment parameter matrix through chi-square anomaly detection based on the multi-modal balance sensor time synchronization signal.

3. The error monitoring method according to claim 1, characterized in that The acquisition of the balance dynamic tensor coupling information in step S2 specifically includes: S201: The balance dynamic tensor coupling information includes a balance dynamic weight tensor and a balance interference coupling coefficient matrix; S202: Obtain a balance dynamic weight tensor through training of a physical constraint tensor network based on the multi-modal balance environment parameter matrix; S203: Obtain a balance interference coupling coefficient matrix through sliding window covariance calculation based on the balance dynamic weight tensor and the multi-modal balance environment parameter matrix.

4. The error monitoring method according to claim 3, wherein The structure of the physical constraint tensor network in step S202 specifically includes: S202-1: The physical constraint tensor network includes an input layer, a hidden layer, and an output layer. The input layer receives the multi-modal balance environment parameter matrix. The hidden layer extracts balance multi-field coupling features through a third-order tensor convolution kernel, and updates the balance dynamic weight tensor based on the balance multi-field coupling features through an adaptive moment estimation optimizer; S202-2: The mathematical expression of the loss function of the physical constraint tensor network is: ， where \(L\) is the physical constraint tensor network loss term, \(m\) is the physical constraint weight coefficient, \(S\) T is the Laplacian operator of the temperature field, \(k\) is the thermal diffusivity, is the rate of change of temperature with respect to time, \(\|\cdot\|\) F is the Frobenius norm of the multi-modal balance environment parameter matrix.

5. The error monitoring method according to claim 1, wherein The calculation process of the balance dynamic error range in step S3 includes: S301: Obtain the standard deviation of the total balance error through a multi-field coupling equation based on the balance dynamic tensor coupling information; S302: Obtain a balance dynamic error range through confidence interval dynamic boundary calculation based on the standard deviation of the total balance error.

6. The error monitoring method according to claim 5, characterized in that The mathematical expression of the multi-field coupling equation in step S301 is: ， Among them, H is the standard deviation of the total error of the balance, W i is the weight of the i-th environmental parameter, E i is the value of the i-th environmental parameter, P ij is the coupling coefficient between the i-th environmental parameter and the j-th environmental parameter, and n is the number of environmental parameters.

7. The error monitoring method according to claim 1, characterized in that, The generation process of the balance error correction information in step S4 specifically includes: S401: Obtain environmental interference error information through multi-modal environmental interference degree analysis based on the balance dynamic error range. The environmental interference error information includes an environmental interference error coefficient and an environmental stability index; S402: Preset an error correction control rule library, and generate balance error correction information through the error correction control rule library based on the environmental interference error information.

8. An error monitoring system adapted to a balance with a precision of one ten-thousandth, applied to the error monitoring method according to any one of claims 1-7, characterized in that Including a multi-modal balance environment parameter matrix acquisition module, a balance dynamic tensor coupling module, a balance dynamic error range calculation module, and a balance error correction visualization module; The multimodal balance environmental parameter matrix acquisition module is used to acquire multimodal balance sensor signals and obtain a multimodal balance environmental parameter matrix through spatio-temporal alignment verification; The balance dynamic tensor coupling module is used to obtain balance dynamic tensor coupling information through a physical constraint tensor network according to the multimodal balance environmental parameter matrix; The balance dynamic error range calculation module is used to obtain a balance dynamic error range through a multi-field coupling equation according to the balance dynamic tensor coupling information; The balance error correction visualization module is used to obtain balance error correction information through multimodal environmental interference degree analysis according to the balance dynamic error range and output a balance error correction visualization diagram.

9. An electronic device, comprising a memory, a processor, and a computer program stored on the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the error monitoring method described in any one of claims 1-7.

10. A storage medium containing computer-executable instructions, characterized in that, The computer-executable instructions are used to execute the error monitoring method described in any one of claims 1-7 when executed by a computer processor.

Images