A Metallurgical On-Site CO Infrared Remote Sensing Identification Method Based on Multi-Feature Spectral Fusion
By employing multi-feature spectral fusion technology and utilizing Savitzky-Golay filtering and Fisher-Z transform to process CO infrared remote sensing identification at metallurgical sites, the accuracy problem of CO leakage detection under low signal-to-noise ratio was solved, achieving CO identification with high sensitivity and low false alarm.
Patent Information
- Application Number
- CN202610168907.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2026-02-05
- Publication Date
- 2026-11-10
- Estimated Expiration
- 2046-02-05
AI Technical Summary
Existing CO leak detection technologies have low accuracy under low signal-to-noise ratio conditions, and local features are submerged, leading to missed detections. Furthermore, the judgment results are subject to statistical bias.
A multi-feature spectral fusion method is adopted, which processes the spectrum through the Savitzky-Golay smoothing filter algorithm, segments it into local sub-bands and global trend features, uses the Top-K selection strategy to screen effective sub-bands, and performs nonlinear fusion through Fisher-z transform, combining local sub-bands and global trend features for decision-making.
It improves anti-interference capability, enhances the sensitivity and confidence of CO identification, and reduces false alarms caused by background fluctuations.
Smart Images

Figure CN122217901B_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of CO detection technology in metallurgical fields, and in particular to a method for identifying CO in metallurgical fields using infrared remote sensing based on multi-feature spectral fusion. Background Technology
[0002] Fourier transform infrared spectroscopy (FTIR) technology is widely used in industrial safety monitoring due to its long-distance and non-contact characteristics. In the metallurgical industry, FTIR can be used to monitor CO leaks in blast furnace gas and coke oven gas. Passive FTIR relies on the radiative temperature difference between the target gas and the background to generate a spectral signal. According to the Beer-Lambert law, the gas is identified by analyzing the characteristic absorption peaks in the spectrum.
[0003] Currently available CO leak detection technologies can be summarized as follows: (1) Single-line peak method: The presence of gas is determined by the height of the strongest one or a few characteristic spectral lines. Its disadvantage is that it is easily affected by accidental noise spikes, which can lead to false alarms.
[0004] (2) Full-spectrum correlation coefficient matching method: The measured spectrum is compared with the standard template spectrum across the entire characteristic band (e.g., 2000-2250 cm⁻¹). -1 The method involves calculating the Pearson correlation coefficient. Its drawback is that it assumes the noise is uniformly distributed white noise. However, in actual industrial environments, noise is non-uniform (colored noise). If a certain band is blocked by strong interference (such as water vapor absorption or inherent instrument noise), this "bad" data will lower the overall correlation score, causing other bands to be judged as having no gas (missed detection). Furthermore, since the Pearson correlation coefficient is non-linear near 1, directly calculating the weighted average of the correlation coefficients of multiple bands will introduce numerical bias, thereby reducing the confidence level of the decision.
[0005] (3) Simple multi-band averaging method: Divide the spectrum into several segments, calculate the correlation, and then take the average value directly. Its disadvantages are: invalid bands are not eliminated, and the direct averaging of correlation coefficients is not statistically rigorous.
[0006] In summary, existing CO leak detection technologies have the following drawbacks: (1) Identification challenges under low signal-to-noise ratio (SNR): Due to the small temperature difference between the leaked gas and the background, and the presence of strong background radiation and instrument noise in the industrial site, the CO characteristic signal is extremely weak and the signal-to-noise ratio is extremely low.
[0007] (2) Local features being submerged, leading to missed detections: The noise in industrial sites is non-white noise, which is frequency-dependent and subject to interference such as water vapor, causing some characteristic spectral lines of CO to be completely submerged. Traditional full-spectrum matching algorithms suffer from low recognition accuracy due to the drag from high-noise bands.
[0008] (3) Statistical bias problem: Traditional methods directly perform arithmetic averaging when fusing multiple features, ignoring the nonlinear distribution characteristics of the correlation coefficient in the high correlation region, resulting in statistical bias in the judgment results. Summary of the Invention
[0009] This invention provides a metallurgical field CO infrared remote sensing identification method based on multi-feature spectral fusion, to solve the technical problems of low identification accuracy under low signal-to-noise ratio, missed detection due to local feature submersion, and statistical bias in the decision results in the existing technology.
[0010] To solve the above-mentioned technical problems, the present invention provides the following technical solution: On one hand, the present invention provides a method for CO infrared remote sensing identification in metallurgical fields based on multi-feature spectral fusion, the method comprising: The radiance spectrum of the metallurgical site is collected, and the collected radiance spectrum is preprocessed to obtain the absorbance spectrum corresponding to the radiance spectrum, which is used as the absorbance spectrum to be detected. Extract the local sub-band features and global trend features of the absorbance spectrum to be detected; The local sub-band features and global trend features of the absorbance spectrum to be detected are fused to obtain the decision statistic of the absorbance spectrum to be detected. If the statistical value of the judgment is greater than the preset threshold, it is determined that CO gas exists at the metallurgical site.
[0011] Further, the process of collecting the radiance spectrum from the metallurgical site and preprocessing the collected radiance spectrum to obtain the absorbance spectrum corresponding to the radiance spectrum includes: The radiance spectrum of the metallurgical site was collected using a Fourier transform infrared spectrometer. The collected radiance spectrum is filtered using a preset filtering algorithm. The filtered radiance spectrum is converted into an absorbance spectrum.
[0012] Furthermore, the preset filtering algorithm is the Savitzky-Golay smoothing filtering algorithm.
[0013] Furthermore, the extraction process of the local sub-band features includes: A peak-finding algorithm was used to identify all independent absorption peaks in the standard CO absorption coefficient spectrum. Then, using adjacent valleys as boundaries, the standard CO absorption coefficient spectrum was divided into multiple independent sub-bands. Simultaneously, a peak-finding algorithm was used to identify all independent absorption peaks in the absorbance spectrum to be detected. Then, using adjacent valleys as boundaries, the absorbance spectrum to be detected was divided into multiple independent sub-bands. The number of sub-bands divided from the standard CO absorption coefficient spectrum was the same as the number of sub-bands divided from the absorbance spectrum to be detected. M ; For each subband of the absorbance spectrum to be detected, calculate its correlation coefficient with the corresponding subband in the standard CO absorption coefficient spectrum; The weight of each subband is determined based on the integral area under each subband in the standard CO absorption coefficient spectrum; the larger the integral area under the subband, the greater the weight of the corresponding subband. Using the Top-K selection strategy, subbands of the absorbance spectrum to be detected are selected. K Each sub-band; among them K greater than 0 and less than M The preset integer value; Based on the Fisher-Z transform, and according to the weights of each subband, the selected... K The sub-bands are nonlinearly fused to obtain local sub-band features.
[0014] Furthermore, the correlation coefficient between each subband of the absorbance spectrum to be detected and the corresponding subband in the standard CO absorption coefficient spectrum is expressed as the Pearson correlation coefficient.
[0015] Furthermore, the Top-K selection strategy is used to screen out sub-bands from all sub-bands of the absorbance spectrum to be detected. K The sub-bands are selected specifically by using a Top-K selection strategy, based on the correlation coefficient between each sub-band of the absorbance spectrum to be detected and the corresponding sub-band in the standard CO absorption coefficient spectrum. K He has a belt.
[0016] Furthermore, based on the Fisher-Z transform, the selected sub-bands are weighted according to their respective weights. K The sub-bands are nonlinearly fused to obtain local sub-band features, including: Mapping the correlation coefficient of each selected subband to the normal distribution space, the formula is as follows: ; in, The first part of the absorbance spectrum to be detected represents the... i The first subband and the standard CO absorption coefficient spectrum i The correlation coefficient of each sub-band; express The mapping value; The weights of all sub-bands are normalized, and then a weighted average is calculated. The formula is expressed as: ; in, Represents the normalized i-th i The weight of each sub-band; Will Restored to the correlation coefficient after fusion , as a local sub-band feature.
[0017] Furthermore, the process of extracting the global trend features includes: The low-frequency envelope curves of the standard CO absorption coefficient spectrum and the absorbance spectrum to be detected were extracted. The correlation coefficient between the low-frequency envelope curve of the absorbance spectrum to be detected and the low-frequency envelope curve of the standard CO absorption coefficient spectrum is calculated and used as a global trend feature.
[0018] Furthermore, the extraction of the low-frequency envelope curve of the standard CO absorption coefficient spectrum and the low-frequency envelope curve of the absorbance spectrum to be detected specifically involves: extracting the low-frequency envelope curve of the standard CO absorption coefficient spectrum and the low-frequency envelope curve of the absorbance spectrum to be detected through Gaussian smoothing. The correlation coefficient between the low-frequency envelope curve of the absorbance spectrum to be detected and the low-frequency envelope curve of the standard CO absorption coefficient spectrum is expressed as the Pearson correlation coefficient.
[0019] Furthermore, the statistics of judgments The calculation formula is: ; in, The preset fusion factor; This represents local sub-band characteristics; This represents the overall trend characteristics.
[0020] In another aspect, the present invention also provides an electronic device comprising a processor and a memory; wherein the memory stores at least one instruction, which is loaded and executed by the processor to implement the above-described method.
[0021] In another aspect, the present invention also provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the above-described method.
[0022] The beneficial effects of the technical solution provided by this invention include at least the following: Strong anti-interference capability: This invention uses a Top-K selection strategy to automatically ignore bands contaminated by noise and only uses the "high-quality" spectral lines with the highest signal-to-noise ratio for decision-making, thus having a stronger anti-interference capability.
[0023] High sensitivity: Even when most features are obscured and only a few feature spectral lines are visible, the technical solution of this invention can still accurately identify CO.
[0024] Statistically rigorous: This invention introduces Fisher-Z transform to correct statistical biases in the fusion process and improve the recognition confidence under low signal-to-noise ratio conditions.
[0025] Dual verification: This invention combines microscopic (spectral lines) and macroscopic (trend) dual-channel features to effectively reduce false alarms caused by background fluctuations. Attached Figure Description
[0026] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0027] Figure 1 This is a schematic diagram of the execution flow of the metallurgical field CO infrared remote sensing identification method based on multi-feature spectral fusion provided in the embodiments of the present invention; Figure 2 This is a schematic diagram of subband segmentation of the CO spectrum provided in an embodiment of the present invention; Figure 3 This is a system block diagram of the electronic device provided in the embodiments of the present invention. Detailed Implementation
[0028] To make the objectives, technical solutions, and advantages of the present invention clearer, the embodiments of the present invention will be described in further detail below with reference to the accompanying drawings.
[0029] First, it should be noted that in the embodiments of the present invention, the words "exemplarily," "for example," etc., are used to indicate that they are examples, illustrations, or descriptions. Any embodiment or design scheme described as "exemplary" in the present invention should not be construed as being more preferred or advantageous than other embodiments or design schemes. Specifically, the use of the term "exemplarily" is intended to present the concept in a specific manner. Furthermore, in the embodiments of the present invention, the meaning expressed by "and / or" can be both, or it can be either one or the other.
[0030] First Embodiment To address the technical challenges of monitoring carbon monoxide (CO) gas using passive Fourier transform infrared (FTIR) telemetry systems in complex environments such as the metallurgical industry, this embodiment provides a method for CO infrared telemetry identification in metallurgical fields based on multi-feature spectral fusion. This method can be implemented using electronic devices, such as terminals or servers. The core of this method lies in decomposing the spectrum into "slowly varying trends" and "fine sub-bands," selecting effective sub-bands using a Top-K strategy, and performing statistical fusion using Fisher-Z transform. The implementation process can be summarized as follows: spectral acquisition… Preprocessing (denoising / baseline correction) Eigenvalue decomposition (trend term extraction + sub-band segmentation) Local feature calculation (Top-K selection + Fisher-Z fusion) Global trend calculation Dual-channel weighted decision Output results.
[0031] Specifically, the execution flow of this method is as follows: Figure 1 As shown, it includes the following steps: S1. Collect the radiance spectrum of the metallurgical site and preprocess the collected radiance spectrum to obtain the absorbance spectrum corresponding to the radiance spectrum, which is used as the absorbance spectrum to be detected. Specifically, in this embodiment, the implementation process of S1 is as follows: S11, Fourier transform infrared spectrometer was used to collect the radiance spectrum of the metallurgical site; S12 uses a preset filtering algorithm to filter the acquired radiance spectrum to remove high-frequency random noise while maintaining the peak shape and half-width at half-maximum. The filtering algorithm can be the Savitzky-Golay smoothing filter algorithm; alternatively, wavelet transform can be used instead of the Savitzky-Golay smoothing filter algorithm for denoising and feature extraction.
[0032] S13 converts the filtered radiance spectrum into an absorbance spectrum, which is then used as input for subsequent processing.
[0033] S2, extract the local sub-band features and global trend features of the absorbance spectrum to be detected; Specifically, in this embodiment, the implementation process of S2 is as follows: S21, using a peak-finding algorithm in the standard CO absorption coefficient spectrum (2000–2250 cm⁻¹) -1 All independent absorption peaks were identified in the sample, and then the standard CO absorption coefficient spectrum was divided into multiple independent subbands, with adjacent troughs as boundaries (for CO, it can usually be divided into about 40 subbands, such as...). Figure 2(As shown); simultaneously, a peak-finding algorithm is used to identify all independent absorption peaks in the absorbance spectrum to be detected. Then, using adjacent valleys as boundaries, the absorbance spectrum to be detected is divided into multiple independent sub-bands; among them, the number of sub-bands divided by the standard CO absorption coefficient spectrum is the same as the number of sub-bands divided by the absorbance spectrum to be detected, which is... M ; S22, Gaussian smoothing is applied to the standard CO absorption coefficient spectrum to extract the low-frequency envelope curve reflecting the overall energy distribution of CO, denoted as... Simultaneously, the absorbance spectrum to be detected is Gaussian smoothed to extract the low-frequency envelope curve reflecting the overall energy distribution of CO in the absorbance spectrum to be detected. It should be noted that polynomial fitting can also be used instead of Gaussian smoothing for global trend extraction.
[0034] S23, for each subband of the absorbance spectrum to be detected Calculate its Pearson correlation coefficient with the corresponding subband in the standard CO absorption coefficient spectrum. (Spearman's rank correlation coefficient can also be used). S24. Determine the weight of each subband based on the integral area under each subband in the standard CO absorption coefficient spectrum; where the larger the integral area under the subband, the more significant the feature, and the greater the weight of the corresponding subband. S25 utilizes a Top-K selection strategy to screen out subbands from all subbands of the absorbance spectrum to be detected. K Individual bands; the specific screening process is as follows: S251, set a parameter ( ); S252, sort all subbands according to the calculated correlation coefficient or signal-to-noise ratio index; S253, only select the top-ranked ones. Subbands are used in subsequent calculations, and subbands that rank lower (i.e. may be submerged or interfered with by noise) are removed.
[0035] S26, based on the Fisher-Z transform, according to the weights of each sub-band, the selected... K The K subbands are nonlinearly fused to obtain local subband features. It should be noted that, to address the statistical bias problem of directly averaging correlation coefficients, this embodiment performs nonlinear fusion on the selected K subbands, employing a Fisher-Z weighted fusion mechanism. During the spectral feature fusion process, the Fisher-Z transform is used to map the Pearson correlation coefficients to a linear space for weighting, followed by an inverse transformation back to the correlation coefficient domain. The specific process is as follows: S261, mapping the correlation coefficient of each selected subband to the normal distribution space: ; in, The first part of the absorbance spectrum to be detected represents the... i The first subband and the standard CO absorption coefficient spectrum i The correlation coefficient of each sub-band; express The mapping value; S262, normalize the weights of all sub-bands, and then calculate the weighted average. The formula is expressed as: ; in, Represents the normalized i-th i The weight of each sub-band; S263, will Restored to the correlation coefficient after fusion , as a local sub-band feature; where z represents the mapping value; e It is the base of natural numbers.
[0036] Based on the above scheme, this embodiment does not use the full spectrum in CO gas identification. Instead, it divides the characteristic bands into multiple sub-bands and adaptively selects the first sub-band based on real-time signal-to-noise ratio or correlation. The optimal sub-bands are fused for identification. This can effectively avoid strong local noise interference and improve the identification accuracy.
[0037] S27. Calculate the Pearson correlation coefficient (or Spearman rank correlation coefficient) between the low-frequency envelope curve of the absorbance spectrum to be detected and the low-frequency envelope curve of the standard CO absorption coefficient spectrum, as a global trend feature. .
[0038] S3, fuse the local sub-band features and global trend features of the absorbance spectrum to be detected to obtain the decision statistic of the absorbance spectrum to be detected; Specifically, in this embodiment, the decision statistic... The calculation formula is: ; in, This is a preset fusion factor, with a value ranging from 0.6 to 0.8. Of course, its value can also be non-fixed, and can be dynamically adjusted based on environmental parameters through machine learning algorithms (such as logistic regression).
[0039] S4, if the decision statistic is greater than a preset threshold T If so, it is determined that CO gas is present at the metallurgical site; It should be noted that the preset threshold T The settings can be customized based on the specific scenario and experience. Furthermore, Support Vector Machines (SVMs) or Neural Networks can be used to replace the linear weighting formula in S3, by... and The features are used as input to support vector machines or neural networks to classify and identify the presence of CO.
[0040] In summary, this embodiment provides a method for CO infrared remote sensing identification in metallurgical fields based on multi-feature spectral fusion. This method automatically ignores noise-contaminated bands using a Top-K selection strategy, utilizing only the "high-quality" spectral lines with the highest signal-to-noise ratio for decision-making, resulting in stronger anti-interference capabilities. Even when most features are obscured, leaving only a few visible spectral lines, the CO infrared remote sensing identification method in metallurgical fields described in this embodiment can still accurately identify CO. Furthermore, this embodiment introduces Fisher-Z transform to correct statistical biases during the fusion process, improving the identification confidence under low signal-to-noise ratio conditions. Simultaneously, this embodiment combines microscopic (spectral lines) and macroscopic (trend) dual-channel features, effectively reducing false alarms caused by background fluctuations.
[0041] Second Embodiment This embodiment provides an electronic device, such as... Figure 3 As shown, the electronic device includes a processor and a memory; wherein the processor and the memory can be connected via a communication bus; the memory stores at least one instruction, which is loaded and executed by the processor to implement the method of the first embodiment described above. Furthermore, the electronic device may also include a transceiver, the processor and the transceiver can be connected via a communication bus, and the transceiver is used to communicate with other devices.
[0042] Below, in conjunction with Figure 3 A detailed introduction to each component of this electronic device is provided below: The processor is the control center of the electronic device. The electronic device may include multiple processors, each of which can be a single-core processor (single-CPU) or a multi-core processor (multi-CPU). The term "processor" can refer to a single processor or a collective term for multiple processing elements. For example, a processor can be one or more central processing units (CPUs), other general-purpose processors, application-specific integrated circuits (ASICs), or one or more integrated circuits configured to implement embodiments of the present invention, such as one or more digital signal processors (DSPs), one or more field-programmable gate arrays (FPGAs), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor can be a microprocessor or any conventional processor. The processor can perform various functions of the electronic device by running or executing software programs stored in memory and by calling data stored in memory.
[0043] In a specific implementation, as one example, the processor may include one or more CPUs, for example... Figure 3 CPU0 and CPU1 shown are, of course, merely illustrative examples.
[0044] The memory is used to store the software program that executes the solution of the present invention, and the processor controls its execution. For specific implementation methods, please refer to the above method embodiments, which will not be repeated here.
[0045] Optionally, the memory may be a read-only memory (ROM) or other type of static storage device capable of storing static information and instructions, random access memory (RAM) or other type of dynamic storage device capable of storing information and instructions, or electrically erasable programmable read-only memory (EEPROM), compact disc read-only memory (CD-ROM) or other optical disc storage, optical disc storage (including compressed optical discs, laser discs, optical discs, digital universal optical discs, Blu-ray discs, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible by a computer, but not limited thereto. The memory may be integrated with the processor or exist independently, and may be accessed through the interface circuit of the electronic device ( Figure 3 (Not shown in the image) is coupled to the processor; however, this embodiment of the invention does not impose specific limitations on this.
[0046] The transceiver may include a receiver and a transmitter. Figure 3 (Not shown separately). The receiver is used to implement the receiving function, and the transmitter is used to implement the transmitting function. The transceiver can be integrated with the processor or exist independently, and can be connected through the interface circuit of the electronic device (…). Figure 3 (Not shown in the image) is coupled to the processor, and this embodiment of the invention does not specifically limit this.
[0047] In addition, it should be noted that, Figure 3 The structure of the electronic device shown is not intended to limit the device. Actual devices may include more or fewer components than shown, or combine certain components, or have different component arrangements. Furthermore, the technical effects achieved by this electronic device when performing the method of the first embodiment described above can be referenced to the technical effects described in the first embodiment; therefore, they will not be repeated here.
[0048] Third Embodiment This embodiment provides a computer-readable storage medium storing at least one instruction, which is loaded and executed by a processor to implement the method of the first embodiment described above. The computer-readable storage medium may be a ROM, random access memory, CD-ROM, magnetic tape, floppy disk, or optical data storage device, etc. The instruction stored therein can be loaded and executed by a processor in a terminal.
[0049] Furthermore, it should be noted that the present invention can be provided as a method, apparatus, or computer program product. Therefore, embodiments of the present invention can take the form of a completely or partially hardware embodiment, a completely or partially software embodiment, or an embodiment combining software and hardware aspects. Moreover, when implemented in software, embodiments of the present invention can take the form of a computer program product implemented on one or more computer-usable storage media containing computer-usable program code. The computer program product includes one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, all or part of the processes or functions described in the embodiments of the present invention are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any usable medium accessible to a computer or a data storage device such as a server or data center containing one or more sets of usable media. The available medium can be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. A semiconductor medium can be a solid-state drive (SSD).
[0050] Embodiments of the present invention are described with reference to flowchart illustrations and / or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, generate instructions for implementing the flowchart illustrations. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.
[0051] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing terminal device to operate in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1The functions specified in one or more boxes. These computer program instructions may also be loaded onto a computer or other programmable data processing terminal equipment to cause a series of operational steps to be performed on the computer or other programmable terminal equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable terminal equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.
[0052] It should also be noted that, in this document, relational terms such as "first" and "second" are used only to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. The terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or terminal device that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or terminal device. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or terminal device that includes said element. Furthermore, the term "and / or" is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, and B alone, where A and B can be singular or plural. Additionally, the character " / " in this text generally indicates an "or" relationship between the preceding and following objects, but it can also indicate an "AND / OR" relationship. Please refer to the context for specific interpretations. "At least one" refers to one or more items, while "more than" refers to two or more items. "At least one of the following" or similar expressions refer to any combination of these items, including any combination of single or multiple items. For example, at least one of a, b, or c can be represented as: a, b, c, ab, ac, bc, or abc, where a, b, and c can be single or multiple.
[0053] Furthermore, it is understood that in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.
[0054] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.
[0055] In the several embodiments provided by this invention, it should be understood that the disclosed devices, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of functional modules / units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another device, or some features may be ignored or not executed. Furthermore, the shown or discussed mutual couplings or direct couplings or communication connections may be through some interfaces; indirect couplings or communication connections between devices or units may be electrical, mechanical, or other forms. Units described as separate components may or may not be physically separate, and components shown as units may or may not be physical units, i.e., they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs. Additionally, the functional units in the various embodiments of this invention 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.
[0056] If the method is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0057] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention. It should be pointed out that although preferred embodiments of the present invention have been described, those skilled in the art, once they understand the basic inventive concept of the present invention, can make several improvements and modifications without departing from the principles described herein. These improvements and modifications should also be considered within the scope of protection of the present invention. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the embodiments of the present invention.
Claims
1. A method for on-site CO infrared remote sensing identification in metallurgical applications based on multi-feature spectral fusion, characterized in that, The metallurgical field CO infrared remote sensing identification method based on multi-feature spectral fusion includes: The radiance spectrum of the metallurgical site is collected, and the collected radiance spectrum is preprocessed to obtain the absorbance spectrum corresponding to the radiance spectrum, which is used as the absorbance spectrum to be detected. Extract the local sub-band features and global trend features of the absorbance spectrum to be detected; The local sub-band features and global trend features of the absorbance spectrum to be detected are fused to obtain the decision statistic of the absorbance spectrum to be detected. If the judgment statistic is greater than the preset threshold, it is determined that CO gas exists at the metallurgical site. The extraction process of the local sub-band features includes: A peak-finding algorithm was used to identify all independent absorption peaks in the standard CO absorption coefficient spectrum. Then, using adjacent valleys as boundaries, the standard CO absorption coefficient spectrum was divided into multiple independent sub-bands. Simultaneously, a peak-finding algorithm was used to identify all independent absorption peaks in the absorbance spectrum to be detected. Then, using adjacent valleys as boundaries, the absorbance spectrum to be detected was divided into multiple independent sub-bands. The number of sub-bands divided from the standard CO absorption coefficient spectrum was the same as the number of sub-bands divided from the absorbance spectrum to be detected. M ; For each subband of the absorbance spectrum to be detected, calculate its correlation coefficient with the corresponding subband in the standard CO absorption coefficient spectrum; The weight of each subband is determined based on the integral area under each subband in the standard CO absorption coefficient spectrum; the larger the integral area under the subband, the greater the weight of the corresponding subband. Using the Top-K selection strategy, subbands of the absorbance spectrum to be detected are selected. K Each sub-band; among them K greater than 0 and less than M The preset integer value; Based on the Fisher-Z transform, and according to the weights of each subband, the selected... K The sub-bands are nonlinearly fused to obtain local sub-band features; The process of extracting the global trend features includes: The low-frequency envelope curves of the standard CO absorption coefficient spectrum and the absorbance spectrum to be detected were extracted. The correlation coefficient between the low-frequency envelope curve of the absorbance spectrum to be detected and the low-frequency envelope curve of the standard CO absorption coefficient spectrum is calculated and used as a global trend feature.
2. The method for CO infrared remote sensing and identification in metallurgical fields based on multi-feature spectral fusion as described in claim 1, characterized in that, The process involves collecting the radiance spectrum from the metallurgical site and preprocessing the collected radiance spectrum to obtain the absorbance spectrum corresponding to the radiance spectrum, including: The radiance spectrum of the metallurgical site was collected using a Fourier transform infrared spectrometer. The collected radiance spectrum is filtered using a preset filtering algorithm. The filtered radiance spectrum is converted into an absorbance spectrum.
3. The method for CO infrared remote sensing and identification in metallurgical fields based on multi-feature spectral fusion as described in claim 2, characterized in that, The preset filtering algorithm is the Savitzky-Golay smoothing filtering algorithm.
4. The method for CO infrared remote sensing identification in metallurgical fields based on multi-feature spectral fusion as described in claim 1, characterized in that, The correlation coefficient between each subband of the absorbance spectrum to be detected and the corresponding subband in the standard CO absorption coefficient spectrum is expressed as the Pearson correlation coefficient.
5. The method for CO infrared remote sensing and identification in metallurgical fields based on multi-feature spectral fusion as described in claim 1, characterized in that, The Top-K selection strategy is used to screen out subbands from all subbands of the absorbance spectrum to be detected. K The sub-bands are selected specifically by using a Top-K selection strategy, based on the correlation coefficient between each sub-band of the absorbance spectrum to be detected and the corresponding sub-band in the standard CO absorption coefficient spectrum. K He has a belt.
6. The method for CO infrared remote sensing and identification in metallurgical fields based on multi-feature spectral fusion as described in claim 1, characterized in that, The Fisher-Z transform-based method, according to the weights of each sub-band, is used to select... K The sub-bands are nonlinearly fused to obtain local sub-band features, including: Mapping the correlation coefficient of each selected subband to the normal distribution space, the formula is as follows: ; in, The first part of the absorbance spectrum to be detected represents the... i The first subband and the standard CO absorption coefficient spectrum i The correlation coefficient of each sub-band; express The mapping value; The weights of all sub-bands are normalized, and then a weighted average is calculated. The formula is expressed as: ; in, Represents the normalized i-th i The weight of each sub-band; Will Restored to the correlation coefficient after fusion , as a local sub-band feature.
7. The method for CO infrared remote sensing and identification in metallurgical fields based on multi-feature spectral fusion as described in claim 1, characterized in that, The extraction of the low-frequency envelope curve of the standard CO absorption coefficient spectrum and the low-frequency envelope curve of the absorbance spectrum to be detected is specifically performed by: extracting the low-frequency envelope curve of the standard CO absorption coefficient spectrum and the low-frequency envelope curve of the absorbance spectrum to be detected through Gaussian smoothing. The correlation coefficient between the low-frequency envelope curve of the absorbance spectrum to be detected and the low-frequency envelope curve of the standard CO absorption coefficient spectrum is expressed as the Pearson correlation coefficient.
8. The method for CO infrared remote sensing and identification in metallurgical fields based on multi-feature spectral fusion as described in claim 1, characterized in that, Judgment statistics The calculation formula is: ; in, The preset fusion factor; This represents local sub-band characteristics; This represents the overall trend characteristics.
Citation Information
Patent Citations
Cigarette case authenticity detection method and device, electronic equipment and storage medium
CN114693589A
