Ash content analysis device and method
By migrating the ash analysis operation to the database and using built-in functions for screening and calculation, the problem of terminal equipment resource occupation and efficiency reduction is solved, and efficient and accurate ash analysis is achieved.
Patent Information
- Application Number
- CN202411190556.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-28
- Publication Date
- 2024-12-06
- Estimated Expiration
- 2044-08-28
AI Technical Summary
In the prior art, ash analysis results in severe storage and computing resource usage when executed on a terminal device, reduced efficiency and accuracy, and may have problems such as memory crashes and data leakage.
Migrate operations in ash analysis to the database, use the database built-in functions for filtering and calculating, and the terminal device only obtains the intermediate calculation results for ash value calculation, avoiding a large amount of memory access.
It significantly saves the storage and computing resources of terminal devices, improves the efficiency and accuracy of ash analysis, and avoids problems such as memory crashes and data leakage.
Smart Images

Figure CN119089215A_ABST
Abstract
Description
Technical Field
[0001] The present invention generally relates to an online fluorescence analyzer, and in particular to a device and a method for analyzing ash content of a slurry using the online fluorescence analyzer. Background Art
[0002] In mining operations, it is often necessary to detect and analyze the ash content of mineral materials (e.g., ore, slurry, etc.) to determine the target content and the type and content of impurities therein, so as to subsequently clean and remove impurities from the ore, slurry, etc.
[0003] Fluorescence analyzers can usually be used to determine the target content and the type and content of impurities in the mineral material. In the prior art, fluorescence analyzers have been widely used to perform ash analysis on mineral samples. However, since ash analysis involves the processing of a large amount of fluorescence data, and the determination of various substances contained in the mineral sample and the calculation of their contents based on various ash analysis models (for example, various ash analysis models based on neural networks, etc.), it is usually performed locally and requires a large amount of storage and computing resources in the terminal device. Therefore, as the data accumulates, it will cause serious storage and computing resource occupation, which will lead to a decrease in the efficiency and accuracy of ash analysis, as well as the degradation of terminal device operation. Summary of the invention
[0004] In order to at least solve one or more of the technical problems mentioned above, the present invention proposes a device and method for ash analysis in multiple aspects, making full use of the built-in functions provided by the database to complete simple screening and calculation steps in the database.
[0005] The inventors found that the current database provides a wealth of built-in functions, which are well matched with many screening and calculation operations involved in ash analysis, and the execution efficiency of these built-in functions in the database is higher than the efficiency of these screening and calculation operations involved in the ash analysis method executed on the terminal device. Therefore, some operations in ash analysis can be migrated to the database, and the terminal device only needs to obtain the intermediate calculation results from the database and calculate the ash value of the mineral material based on the intermediate calculation results, which can significantly save the storage and computing resources of the terminal device and improve the efficiency and accuracy of ash analysis. In addition, in an embodiment of the present invention, the terminal device obtains from the database the intermediate calculation results processed by the database, rather than the original stored sampling data. Accordingly, the terminal device only needs to temporarily store these intermediate calculation results and perform ash value calculations based on these intermediate calculation results, so that a large number of memory access operations can be avoided, thereby avoiding problems such as memory crashes and data leaks.
[0006] In a first aspect of the present invention, there is provided an apparatus for ash analysis, comprising: a data acquisition module, the data acquisition module being configured to obtain a fluorescence feature vector of a sample to be tested; a database module, the database module being coupled to the data acquisition module and being configured to use a database function to: obtain the fluorescence feature vector of the sample to be tested from the data acquisition module; search the database for a set of standard sample feature vectors having a similar acquisition time and the same address as the fluorescence feature vector of the sample to be tested, wherein the set of standard sample feature vectors comprises one or more standard sample feature vectors, the standard sample feature vectors indicating the fluorescence reaction characteristics and ash values of the standard samples; calculate the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors; and output a data set to be analyzed based on the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors; and a data analysis module, the data analysis module being coupled to the database module and being configured to calculate the ash value of the sample to be tested based on the data set to be analyzed.
[0007] The device as described above, wherein the database module is further configured to use a database function to: determine whether the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set meets a similarity standard; and in response to determining that the similarity between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set meets the similarity standard, output the data set to be analyzed, wherein the data set to be analyzed indicates a subset of the standard sample feature vector set, and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the standard sample feature vector set includes standard sample feature vectors whose similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard, and wherein the data analysis module is configured to: calculate the ash value of the sample to be tested based on the subset of the standard sample feature vector set and the subset similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset.
[0008] An apparatus as described in any of the above items, wherein the database module is further configured to use a database function to: sort the similarities between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; and output the data set to be analyzed based on the sorting result, wherein a subset of the standard sample feature vector set includes the first N standard sample feature vectors whose similarities with the fluorescence feature vector of the sample to be tested meet the similarity standard, wherein N is an integer not less than 1.
[0009] An apparatus as described in any of the above items, wherein the calculated similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors is a first similarity calculated based on a first similarity algorithm, and wherein the database module is further configured to use a database function to: calculate a second similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors based on a second similarity algorithm, wherein the second similarity algorithm is different from the first similarity algorithm; sort the second similarities between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors; and output the data set to be analyzed based on the sorting result, wherein a subset of the set of standard sample feature vectors includes N standard sample feature vectors whose first similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard and whose second similarity is the highest, wherein N is an integer not less than 1.
[0010] An apparatus as described in any of the above items, wherein the database module is further configured to use a database function to: in response to determining that the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors does not meet the similarity standard, output the data set to be analyzed indicating the fluorescence feature vector of the sample to be tested, and wherein the data analysis module is configured to: calculate the ash value of the sample to be tested according to a sample ash analysis model based on the fluorescence feature vector of the sample to be tested.
[0011] A device as described in any of the above items, wherein the device also includes a database update module, which is coupled to the data analysis module and is configured to: update the database based on the fluorescence feature vector of the sample to be tested whose similarity with each standard sample feature vector in the set of standard sample feature vectors is less than the similarity threshold, and the calculated ash value of the sample to be tested.
[0012] As described in any of the above items, wherein the data acquisition module is configured to generate a fluorescence feature vector of the sample to be tested based on the fluorescence response data of multiple sampling points on the sample to be tested.
[0013] In a second aspect of the present invention, a method for ash analysis is provided, comprising: utilizing a database function to: obtain a fluorescence feature vector of a sample to be tested; searching a database for a set of standard sample feature vectors having a similar acquisition time and the same channel address as the fluorescence feature vector of the sample to be tested, wherein the set of standard sample feature vectors comprises one or more standard sample feature vectors, and the standard sample feature vectors indicate the fluorescence reaction characteristics and ash values of the standard samples; calculating the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors; and outputting a data set to be analyzed based on the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors, wherein the data set to be analyzed is output to a data analysis device through the database, so that the data analysis device calculates the ash value of the sample to be tested based on the data set to be analyzed.
[0014] The method as described above, wherein using a database function to output a data set to be analyzed includes: determining whether the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set satisfies a similarity standard; and in response to determining that the similarity between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set satisfies the similarity standard, outputting the data set to be analyzed, wherein the data set to be analyzed indicates a subset of the standard sample feature vector set, and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the standard sample feature vector set includes standard sample feature vectors whose similarity to the fluorescence feature vector of the sample to be tested satisfies the similarity standard, and wherein the data analysis device calculates the ash value of the sample to be tested based on the subset of the standard sample feature vector set, and the subset similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset.
[0015] A method as described in any of the above items, wherein using a database function to output the data set to be analyzed includes: sorting the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; and outputting the data set to be analyzed based on the sorting result, wherein a subset of the standard sample feature vector set includes the first N standard sample feature vectors whose similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard, wherein N is an integer not less than 1.
[0016] A method as in any of the above items, wherein the calculated similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors is a first similarity calculated based on a first algorithm, and wherein using a database function to output a data set to be analyzed includes: calculating a second similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors based on a second algorithm, the second algorithm being different from the first algorithm; sorting the second similarities between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors; and outputting the data set to be analyzed based on the sorting result, wherein a subset of the set of standard sample feature vectors includes N standard sample feature vectors whose first similarity with the fluorescence feature vector of the sample to be tested satisfies the similarity standard and whose second similarity is the highest, wherein N is an integer not less than 1.
[0017] A method as described in any of the above items, wherein using a database function to output the data set to be analyzed includes: if the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors does not meet the similarity standard, then outputting the data set to be analyzed indicating the fluorescence feature vector of the sample to be tested, and wherein the data analysis device calculates the ash value of the sample to be tested according to a sample ash analysis model based on the fluorescence feature vector of the sample to be tested.
[0018] A method as described in any of the above items, wherein the method further includes: updating the database based on the fluorescence feature vector of the sample to be tested whose similarity with each standard sample feature vector in the standard sample feature vector set is less than the similarity threshold, and the calculated ash value of the sample to be tested.
[0019] In a third aspect of the present invention, an online fluorescence analyzer is provided, comprising: a fluorescence device configured to emit excitation light to a sample to be tested and receive a fluorescence signal from the sample to be tested; and a device as described in any one of the above items.
[0020] In a fourth aspect of the present invention, a machine-readable medium is provided, comprising machine-readable instructions, which, when executed, cause a machine to perform a method as claimed in any one of claims 8 to 13.
[0021] In a fourth aspect of the present invention, there is provided a computer program product comprising computer instructions which, when executed, cause a machine to perform the method as claimed in any one of claims 8 to 13. BRIEF DESCRIPTION OF THE DRAWINGS
[0022] The above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood by reading the detailed description below with reference to the accompanying drawings. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:
[0023] Figure 1 A schematic block diagram showing an ash analysis device according to at least some embodiments of the present invention;
[0024] Figure 2 A schematic flow chart showing an ash analysis method according to at least some embodiments of the present invention;
[0025] Figure 3 A schematic flow chart showing an ash analysis method according to some other embodiments of the present invention;
[0026] Figure 4 A schematic flow chart showing an ash analysis method according to some other embodiments of the present invention;
[0027] Figure 5 A schematic flow chart showing an ash analysis method according to some other embodiments of the present invention; and
[0028] Figure 6 A schematic block diagram of a fluorescence analyzer according to an embodiment of the present invention is shown. DETAILED DESCRIPTION
[0029] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.
[0030] It should be understood that the terms "include" and "comprising" used in the description and claims of the present invention indicate the presence of described features, integers, steps, operations, elements and / or components, but do not exclude the presence or addition of one or more other features, integers, steps, operations, elements, components and / or combinations thereof.
[0031] It should also be understood that the terms used in this specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. As used in the specification of the present invention and the claims, the singular forms of "a", "an" and "the" are intended to include the plural forms unless the context clearly indicates otherwise. It should also be further understood that the term "and / or" used in the specification of the present invention and the claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes these combinations.
[0032] As used in this specification and claims, the term "if" may be interpreted as "when" or "upon" or "in response to determining" or "in response to detecting," depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" may be interpreted as meaning "upon determination" or "in response to determining" or "upon detection of [described condition or event]" or "in response to detecting [described condition or event]," depending on the context.
[0033] Figure 1 An ash analysis device 10 is shown in accordance with at least some embodiments of the present invention.
[0034] like Figure 1 As shown, the ash analysis device 10 may include a data acquisition module 102. According to at least some embodiments of the present invention, the data acquisition module 102 is configured to obtain a fluorescence characteristic vector of a sample to be tested. In at least some embodiments of the present invention, mineral materials can be obtained using mining equipment to prepare mineral material samples having an appropriate physical form (e.g., size, shape, etc.) so that excitation light can be emitted thereto by a light source. The mineral material sample is irradiated with the excitation light and produces a fluorescent reaction, thereby providing a fluorescent signal. According to an embodiment of the present invention, the data acquisition module 102 can obtain a fluorescent signal from the mineral material sample, extract the fluorescent characteristics of the mineral material sample from the fluorescent signal, and generate a fluorescent characteristic vector of the mineral material sample. As an exemplary implementation, the signal peak value of the fluorescent signal in one or more sampling periods can be used as the corresponding fluorescent characteristic value, and the fluorescent characteristic vector of the mineral material sample can be generated based on the fluorescent characteristic value.
[0035] According to at least some embodiments of the present invention, the data acquisition module 102 can obtain fluorescence signals for multiple sampling points on the mineral sample to be tested, and calculate the fluorescence characteristic value based on the fluorescence signals of the multiple sampling points (for example, the fluorescence characteristic values of each sampling point are averaged, etc.). As an exemplary implementation, the mineral sample to be tested can be placed on a conveying mechanism, and the mineral sample to be tested moves through the area below the excitation light source as the conveying mechanism moves, so that the excitation light source irradiates different positions on the mineral sample in different light-emitting rounds, thereby obtaining fluorescence signals from multiple different sampling points. As another exemplary implementation, an end effector can be used to grab the mineral sample to be tested, and rotate it near the excitation light source, so that the excitation light source irradiates different positions on the mineral sample in different light-emitting rounds, and obtains fluorescence signals from multiple different sampling points. According to an embodiment of the present invention, the number of sampling points can be any integer greater than 0, for example, the number of sampling points can be set to 1, 2, 3, 4, 10, 15, 20, etc. According to at least some embodiments of the present invention, taking into account sampling efficiency and calculation accuracy, the data acquisition module 102 can acquire fluorescence signals at four sampling points on the mineral sample to be tested, calculate fluorescence characteristic values based on the fluorescence signals of these sampling points, and finally generate a fluorescence characteristic vector of the mineral sample.
[0036] like Figure 1 As shown, the ash analysis device 10 may include a database module 104, which may be coupled to the data acquisition module 102. According to at least some embodiments of the present invention, the database module 104 may be configured to obtain the fluorescence feature vector of the mineral sample to be tested from the data acquisition module 102 using a database function. As an exemplary implementation, the inset() function may be used to insert the fluorescence feature vector obtained from the data acquisition module 102 into the database. As another exemplary implementation, a database connection tool may be used to automatically read the fluorescence feature vector of the mineral sample to be tested from the data acquisition module 102 into the database.
[0037] According to an embodiment of the present invention, the database used herein may come from various suppliers, and pre-stores feature vectors for various standard samples, wherein the feature vectors of these standard samples indicate the fluorescence reaction characteristics and ash values of the standard samples. According to an embodiment of the present invention, the standard sample is a mineral sample with a known ash value, and the fluorescence reaction characteristics of the standard sample are based on the fluorescence signal obtained by irradiating the standard sample with known ash value with excitation light.
[0038] According to an embodiment of the present invention, the database module 104 may be configured to use a database function to search the database for a set of standard sample feature vectors with a similar acquisition time and the same channel address as the fluorescence feature vector of the sample to be tested. According to an embodiment of the present invention, the set of standard sample feature vectors includes one or more standard sample feature vectors, each of which indicates the fluorescence reaction characteristics and ash value of the corresponding standard sample. As an example, it is assumed that the fluorescence feature vector obtained by the database module 104 from the data acquisition module 102 is based on the fluorescence feature vector collected at the sampling time T and with the channel address C1-C N If the fluorescence signal is obtained, the database module 104 can use the select() function to set the keywords to the sampling time T, the channel address C1-C N , retrieve the standard sample feature vector in the database.
[0039] According to an embodiment of the present invention, the database module 104 may be configured to calculate the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set. As an exemplary implementation, the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set may be calculated. For example, the sum() function, pow() function, etc. may be used to calculate the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set.
[0040] According to an embodiment of the present invention, the database module 104 may also be configured to output the data set to be analyzed based on the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set.
[0041] like Figure 1 As shown, the ash analysis device 10 may further include a data analysis module 106, which may be coupled to the database module 104. According to an embodiment of the present invention, the data analysis module 106 may be configured to calculate the ash value of the sample to be tested based on the data set to be analyzed. As described above, the standard sample is a mineral sample with a known ash value. Therefore, according to an embodiment of the present invention, the ash value of the sample to be tested may be calculated based on the ash value of the standard sample indicated by the data set to be analyzed and similar to the sample to be tested, according to the similarity of the fluorescence reaction.
[0042] According to at least some embodiments of the present invention, the database module 104 can screen the set of standard sample feature vectors obtained from the database search based on similarity, remove the standard sample feature vectors that are not similar to the fluorescence feature vector of the sample to be tested, and output the data to be analyzed based on the standard sample feature vectors that are similar to the fluorescence feature vector of the sample to be tested. On this basis, the data analysis module 106 can calculate the ash value of the sample to be tested based on the ash value of the standard sample that is sufficiently similar to the sample to be tested, thereby reducing the computational complexity and improving the accuracy of the ash analysis.
[0043] According to an embodiment of the present invention, the database module 104 may be configured to determine whether the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set meets a similarity criterion.
[0044] As an exemplary implementation, the database module 104 may calculate the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set, and use the select() function to determine whether there is a standard sample feature vector in the standard sample feature vector set whose Euclidean distance with the fluorescence feature vector of the sample to be tested is less than the Euclidean distance threshold. For example, the select() function may be used to compare the Euclidean distance between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set with the Euclidean distance threshold, and in the case where the Euclidean distance between the fluorescence feature vector of the sample to be tested and the standard sample feature vector is less than the Euclidean distance threshold, the select() function returns "1", and in the case where the Euclidean distance between the fluorescence feature vector of the sample to be tested and the standard sample feature vector is not less than the Euclidean distance threshold, the select() function returns "0".
[0045] According to an embodiment of the present invention, if the database module 104 determines that there are standard sample feature vectors in the standard sample feature vector set whose Euclidean distance to the fluorescence feature vector of the sample to be tested is less than the Euclidean distance threshold (that is, their similarity meets the similarity threshold), the database module 104 can output the data to be analyzed based on these standard sample feature vectors whose Euclidean distance to the fluorescence feature vector of the sample to be tested is less than the Euclidean distance threshold and the corresponding Euclidean distance. As another exemplary implementation, the database module 104 can directly use the select() function to return the sample feature vectors whose similarity meets the similarity standard to obtain the data set to be analyzed. According to an embodiment of the present invention, the data set to be analyzed indicates a subset of the standard sample feature vector set, and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset. According to an embodiment of the present invention, the data analysis module 106 can calculate the ash value of the sample to be tested based on the fluorescence feature value indicated by the standard sample feature vector in the subset of the standard sample feature vector set, the similarity between the corresponding standard sample feature vector and the fluorescence feature vector of the sample to be tested, and the ash value of the corresponding standard sample.
[0046] According to an embodiment of the present invention, if the database module 104 determines that there is no standard sample feature vector in the standard sample feature vector set whose Euclidean distance with the fluorescence feature vector of the sample to be tested is less than the Euclidean distance threshold (that is, the similarity of each standard sample feature vector does not meet the similarity threshold), the database module 104 can output the data set to be analyzed based on the fluorescence feature vector of the sample to be tested. For example, the database module 104 can directly use the select() function to return the sample feature vector whose similarity meets the similarity standard. If the select() function can return "null", it indicates that the database module 104 determines that there is no standard sample feature vector in the standard sample feature vector set whose Euclidean distance with the fluorescence feature vector of the sample to be tested is less than the Euclidean distance threshold. According to an embodiment of the present invention, the similarity between each standard sample feature vector in the standard sample feature vector set and the fluorescence feature vector of the sample to be tested does not meet the similarity standard, which can indicate that there is no relevant data of the standard sample that is sufficiently similar to the sample to be tested and can be used to calculate the ash value of the sample to be tested in the current database. According to an embodiment of the present invention, the data analysis module 106 may calculate the ash value of the sample to be tested according to any known fluorescence ash analysis model and based on various fluorescence features indicated by the fluorescence feature vector of the sample to be tested.
[0047] To further improve the accuracy of ash analysis, in at least one embodiment of the present invention, the database module 104 can further screen a subset of the standard sample feature vector set. As an exemplary implementation, the database module 104 can use the sort() function to sort the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the standard sample feature vector set, and select N (N is an integer not less than 1) standard sample feature vectors with the highest similarity to the fluorescence feature vector of the sample to be tested (for example, the smallest Euclidean distance to the fluorescence feature vector of the sample to be tested), and output the data set to be analyzed based on these N standard sample feature vectors. According to an embodiment of the present invention, the output data set to be analyzed indicates a subset of the standard sample feature vector set, and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the standard sample feature vector set includes the N standard sample feature vectors with the fluorescence feature vector of the sample to be tested.
[0048] The above text describes the similarity between the fluorescence feature vector of the sample to be tested and the feature vector of the standard sample with reference to the Euclidean distance, but those skilled in the art should understand that in other embodiments of the present invention, the cosine similarity, dot product similarity, etc. between the fluorescence feature vector of the sample to be tested and the feature vector of the standard sample can also be calculated.
[0049] According to at least some embodiments of the present invention, the database module 104 may be configured to calculate the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set, and to perform a first screening of the standard sample feature vector set based on whether the Euclidean distance is less than a Euclidean distance threshold to obtain a subset of the standard sample feature vector set. In addition, the database module 104 may be configured to calculate the cosine similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the subset of the standard sample feature vector set, and to sort the cosine similarity, and to output the data set to be analyzed based on the N (N is an integer not less than 1) standard sample feature vectors with the highest cosine similarity to the fluorescence feature vector of the sample to be tested. According to an embodiment of the present invention, the output data set to be analyzed indicates a subset of the standard sample feature vector set, and the cosine similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset. The subset of the standard sample feature vector set includes N (N is an integer not less than 1) standard sample feature vectors whose Euclidean distance with the fluorescence feature vector of the sample to be tested is less than the Euclidean distance threshold and whose cosine similarity with the fluorescence feature vector of the sample to be tested is the highest.
[0050] like Figure 1As shown, the ash analysis device 10 may also optionally include a database update module 108. According to an embodiment of the present invention, the database update module 108 may be coupled to the data analysis module 106 to receive the relevant fluorescence characteristics and ash value of the sample to be tested from the data analysis module 106. According to an embodiment of the present invention, when there is no relevant data of a standard sample similar to the fluorescence characteristic vector of the sample to be tested in the database (for example, the database module 104 determines that the similarity between each standard sample feature vector in the standard sample feature vector set and the fluorescence characteristic vector of the sample to be tested does not meet the similarity threshold), the data analysis module 106 calculates the ash value of the sample to be tested based on the fluorescence ash analysis model, and outputs the fluorescence characteristic vector of the sample to be tested and the calculated ash value to the database update module 108. According to an embodiment of the present invention, the database update module 108 performs data fusion on the fluorescence characteristic vector and ash value of the sample to be tested, and periodically inserts these data into the database to update the database, thereby facilitating the subsequent ash analysis of the sample to be tested.
[0051] As described above, in the ash analysis device proposed in the present invention, the database module uses the built-in functions of the database to perform screening and simple calculations on the original data, so that at least some operations in the ash analysis are migrated to the database, and the data analysis module only needs to obtain the data to be analyzed from the database module (specifically, the ash value of the screened standard sample and the similarity between the sample to be tested and the standard sample) to calculate the ash value of the mineral material, which can significantly save the storage and computing resources of the terminal device and improve the efficiency and accuracy of the ash analysis. In addition, the ash analysis device proposed in the present invention can avoid a large number of memory access operations, thereby avoiding problems such as memory crashes and data leaks.
[0052] The present invention also provides methods for performing ash analysis. The methods provided by the present invention are executed by a database based on database built-in functions.
[0053] Figure 2 A schematic block diagram of an ash analysis method 20 according to an embodiment of the present invention is shown.
[0054] like Figure 2 As shown, method 20 may include: at 202, using a database function to obtain a fluorescence feature vector of a mineral sample to be tested. As an exemplary implementation, the inset() function may be used to insert the fluorescence feature vector of the mineral sample to be tested into the database. As another exemplary implementation, a database connection tool may be used to automatically read the fluorescence feature vector of the mineral sample to be tested into the database.
[0055] like Figure 2As shown, the method 20 may further include: at 204, searching the database for a set of standard sample feature vectors with a similar acquisition time and the same channel address as the fluorescence feature vector of the sample to be tested. According to an embodiment of the present invention, the set of standard sample feature vectors includes one or more standard sample feature vectors, each of which indicates the fluorescence reaction characteristics and ash value of the standard sample. As an example, the fluorescence feature vector of the sample to be tested is based on the standard sample vectors acquired at the sampling time T and with the channel addresses C1-C N If the fluorescence signal is obtained, the select() function can be used to set the keywords to the sampling time T, the channel address C1-C N , retrieve the standard sample feature vector in the database.
[0056] like Figure 2 As shown, the method 20 may further include: at 206, calculating the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set. As an exemplary implementation, the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set may be calculated. For example, the sum() function, pow() function, etc. may be used to calculate the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set.
[0057] like Figure 2 As shown, the method 20 may further include: at 208, outputting the data set to be analyzed based on the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set.
[0058] According to an embodiment of the present invention, the data set to be analyzed is output to a data analysis device of a terminal device (for example, as described above with reference to Figure 1 The described data analysis module 106) is used by the data analysis device to calculate the ash value of the sample to be tested based on the data set to be analyzed.
[0059] As described above, the ash analysis method 20 according to an embodiment of the present invention is executed in the database based on the database built-in function, which can significantly alleviate the storage and computing pressure of the terminal device and avoid a large number of memory access operations, thereby avoiding memory crashes, data leakage and other problems.
[0060] Figure 3 Ash analysis methods 30 according to some other embodiments of the present invention are shown.
[0061] like Figure 3As shown, method 30 may include: at 302, using a database function to obtain a fluorescence feature vector of a mineral sample to be tested; at 304, using a database function to search a database for a set of standard sample feature vectors that have a similar acquisition time and the same channel address as the fluorescence feature vector of the sample to be tested; at 306, using a database function to calculate the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors.
[0062] like Figure 3 As further shown, method 30 may also include: at 308, using a database function to determine whether the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set meets the similarity standard. According to at least some embodiments of the present invention, method 30 may screen the standard sample feature vector set obtained from the database search based on the similarity, and remove the standard sample feature vectors that are not similar to the fluorescence feature vector of the sample to be tested, so as to output the data to be analyzed based on the standard sample feature vector that is similar to the fluorescence feature vector of the sample to be tested. As an exemplary implementation, the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set may be calculated, and the select() function may be used to determine whether there is a standard sample feature vector in the standard sample feature vector set whose Euclidean distance to the fluorescence feature vector of the sample to be tested is less than the Euclidean distance threshold. For example, the select() function can be used to compare the Euclidean distance between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set with a Euclidean distance threshold. When the Euclidean distance between the fluorescence feature vector of the sample to be tested and the standard sample feature vector is less than the Euclidean distance threshold, the select() function returns "1", and when the Euclidean distance between the fluorescence feature vector of the sample to be tested and the standard sample feature vector is not less than the Euclidean distance threshold, the select() function returns "0".
[0063] like Figure 3As shown, the method 30 may also include: in response to determining at 308 that the similarity between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set meets the similarity standard (for example, the Euclidean distance between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set is less than the Euclidean distance threshold), at 310, using a database function to output the data set to be analyzed based on the at least one standard sample feature vector whose similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard. As an exemplary implementation, the data set to be analyzed may be output by the standard sample feature vector corresponding to when the select() function returns "1". According to an embodiment of the present invention, the data set to be analyzed output at 310 may indicate a subset of the standard sample feature vector set, and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the standard sample feature vector set includes the standard sample feature vector whose similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard.
[0064] like Figure 3 As shown, the method 30 may further include: in response to determining at 308 that the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set does not meet the similarity standard (for example, the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set is not less than the Euclidean distance threshold), at 312, the data set to be analyzed may be output based on the fluorescence feature vector of the sample to be tested. According to an embodiment of the present invention, the fact that the similarity between each standard sample feature vector in the standard sample feature vector set and the fluorescence feature vector of the sample to be tested does not meet the similarity standard may indicate that there is no relevant data of a standard sample in the current database that is sufficiently similar to the sample to be tested and can be used to calculate the ash value of the sample to be tested, and thus, the data set to be analyzed is output directly based on the fluorescence feature vector of the sample to be tested.
[0065] According to an embodiment of the present invention, the data set to be analyzed is output to a data analysis device of a terminal device (for example, as described above with reference to Figure 1The described data analysis module 106) is used to calculate the ash value of the sample to be tested based on the data set to be analyzed. Since the data analysis device can calculate the ash value of the sample to be tested based on the ash value of a standard sample that is sufficiently similar to the sample to be tested, the calculation complexity can be reduced and the accuracy of the ash analysis can be improved. According to an embodiment of the present invention, when there is no standard sample that is sufficiently similar to the sample to be tested in the database, the data set to be analyzed based on the fluorescence feature vector of the sample to be tested is output to the data analysis device of the terminal device, and the data analysis device of the terminal device can calculate the ash value of the sample to be tested based on any known fluorescence ash analysis model and various fluorescence features indicated by the fluorescence feature vector of the sample to be tested, thereby further ensuring the calculation of the ash value of the sample to be tested.
[0066] The ash analysis method 30 described in the embodiment of the present invention describes filtering data in a database based on similarity, and outputting the data to be analyzed to a data analysis device of a terminal device based on the filtered data, thereby further alleviating the storage and computing pressure of the terminal device.
[0067] Figure 4 Ash analysis methods 40 according to some other embodiments of the present invention are shown.
[0068] like Figure 4 As shown, method 40 may include: at 402, obtaining the fluorescence characteristic vector of the mineral sample to be tested by using a database function; at 404, searching the database for a set of standard sample characteristic vectors with similar acquisition time and the same channel address as the fluorescence characteristic vector of the sample to be tested by using a database function; at 406, calculating the similarity between the fluorescence characteristic vector of the sample to be tested and each standard sample characteristic vector in the set of standard sample characteristic vectors by using a database function; at 408, determining whether the similarity between the fluorescence characteristic vector of the sample to be tested and each standard sample characteristic vector in the set of standard sample characteristic vectors meets a similarity standard by using a database function; in response to determining at 408 that the similarity between the fluorescence characteristic vector of the sample to be tested and each standard sample characteristic vector in the set of standard sample characteristic vectors does not meet the similarity standard, at 412, outputting the data set to be analyzed based on the fluorescence characteristic vector of the sample to be tested by using a database function.
[0069] In addition, if Figure 4As shown, the method 40 may further include: in response to determining at 408 that the similarity between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set meets the similarity standard (for example, the Euclidean distance between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set is less than the Euclidean distance threshold), at 410, using a database function to sort the similarities between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set. As an exemplary implementation, the sort() function may be used to sort the similarities between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the standard sample feature vector set.
[0070] like Figure 4 As shown, method 40 may further include: at 414, outputting the data set to be analyzed using a database function based on the result of the similarity sorting performed at 410. According to an embodiment of the present invention, the data set to be analyzed output at 410 may indicate a subset of the set of standard sample feature vectors, and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the set of standard sample feature vectors includes the N (N is an integer not less than 1) standard sample feature vectors whose similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard and has the highest similarity. As an exemplary implementation, based on the sorting result of the sort() function, N (N is an integer not less than 1) standard sample feature vectors with the highest similarity to the fluorescence feature vector of the sample to be tested (for example, the one with the smallest Euclidean distance to the fluorescence feature vector of the sample to be tested) may be selected, and the data set to be analyzed may be output based on these N standard sample feature vectors. According to an embodiment of the present invention, the output data set to be analyzed indicates a subset of the standard sample feature vector set and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the standard sample feature vector set includes the N standard sample feature vectors between the fluorescence feature vector of the sample to be tested.
[0071] According to an embodiment of the present invention, the data set to be analyzed is output to a data analysis device of a terminal device (for example, as described above with reference to Figure 1 The described data analysis module 106) is used by the data analysis device to calculate the ash value of the sample to be tested based on the data set to be analyzed.
[0072] According to the method 40 of the embodiment of the present invention, the data in the database is further screened based on the similarity, and the data to be analyzed is output to the data analysis device of the terminal device based on the data after two screenings, so that the data analysis device can calculate the ash value of the sample to be tested based on the ash value of the standard sample that is sufficiently similar to the sample to be tested, thereby further reducing the calculation complexity and improving the accuracy of the ash analysis.
[0073] Figure 5 Ash analysis methods 50 according to some other embodiments of the present invention are shown.
[0074] like Figure 5 As shown, method 50 may include: at 502, using a database function to obtain a fluorescence feature vector of a mineral sample to be tested; at 504, using a database function to search a database for a set of standard sample feature vectors having a similar acquisition time and the same channel address as the fluorescence feature vector of the sample to be tested.
[0075] like Figure 5 As shown, the method 50 may further include: at 506, using the database function and based on the first similarity algorithm to calculate the first similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set. As an exemplary implementation, the database function may be used to calculate the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set to indicate the first similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set.
[0076] like Figure 5 As shown, the method 50 may further include: at 508, determining using a database function whether a first similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set meets a similarity criterion. As an exemplary implementation, it may be determined whether the Euclidean distance between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set is less than a Euclidean distance threshold to perform a similarity test on the standard sample feature vector set, wherein a Euclidean distance less than the Euclidean distance threshold indicates that the first similarity meets the similarity criterion, and a Euclidean distance not less than (i.e., greater than or equal to) the Euclidean distance threshold indicates that the first similarity does not meet the similarity criterion.
[0077] like Figure 5As shown, the method 50 may also include: in response to determining at 508 that the similarity between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set meets the similarity standard (for example, the Euclidean distance between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the standard sample feature vector set is less than the Euclidean distance threshold), at 510, using a database function and a second similarity algorithm to calculate a second similarity between the fluorescence feature vector of the sample to be tested and the at least one standard sample feature vector. According to an embodiment of the present invention, the second similarity algorithm is different from the first similarity algorithm adopted at 506. As an exemplary implementation, the database function may be used to calculate the cosine similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the standard sample feature vector set to indicate the second similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the standard sample feature vector set.
[0078] like Figure 5 As shown, the method 50 may further include: at 514, using a database function to sort the second similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the standard sample feature vector set. As an exemplary implementation, the sort() function may be used to sort the cosine similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the standard sample feature vector set.
[0079] like Figure 5 As shown, the method 50 may also include: at 516, outputting the data set to be analyzed using a database function based on the result of the similarity sorting performed at 514. According to an embodiment of the present invention, the data set to be analyzed output at 516 may indicate a subset of the set of standard sample feature vectors, and a second similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the set of standard sample feature vectors includes N (N is an integer not less than 1) standard sample feature vectors whose first similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard and whose second similarity is the highest. As an exemplary implementation, based on the sorting result of the sort() function, N (N is an integer not less than 1) standard sample feature vectors whose second similarity with the fluorescence feature vector of the sample to be tested is the highest (for example, the cosine similarity with the fluorescence feature vector of the sample to be tested is the highest) are selected, and the data set to be analyzed is output based on these N standard sample feature vectors.
[0080] like Figure 5As shown, method 50 may also include: in response to determining at 508 that the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors does not meet the similarity standard, at 512, using a database function to output the data set to be analyzed based on the fluorescence feature vector of the sample to be tested.
[0081] The above text describes the first similarity and the second similarity between the fluorescence feature vector of the sample to be tested and the feature vector of the standard sample with reference to the Euclidean distance and the cosine similarity, but those skilled in the art should understand that the cosine similarity can also be used as a measure of the first similarity and the Euclidean distance can be used as a measure of the second similarity, and in other embodiments of the present invention, other similarity measures between the fluorescence feature vector of the sample to be tested and the feature vector of the standard sample can also be calculated, such as dot product similarity.
[0082] In the ash analysis method 50 according to an embodiment of the present invention, a first similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set is first calculated based on a first similarity algorithm, and the first similarity is used to screen the data to obtain a subset of the standard sample feature vector set; then, a second similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the subset of the standard sample feature vector set is calculated based on a second similarity algorithm, and the second similarity is used to screen the data again, thereby ensuring that the similarity between the standard sample indicated by the output data to be analyzed and the sample to be tested is high enough, which can significantly alleviate the storage and computing pressure of the terminal device and ensure the accuracy of the ash analysis.
[0083] Figure 6 A schematic block diagram of a fluorescence analyzer 60 according to an embodiment of the present invention is shown.
[0084] like Figure 6 As shown, the fluorescence analyzer 60 may include a fluorescence device 602 and an ash analysis device 10 (e.g., as described above with reference to Figure 1 According to an embodiment of the present invention, the fluorescence device 602 may be coupled to the ash analysis device 10 to provide the fluorescence characteristic data of the sample to be tested to the ash analysis device 10 (specifically, the data acquisition module 102 of the ash analysis device 10). According to an embodiment of the present invention, the fluorescence device 602 may include an excitation light source (not shown) to irradiate the excitation light to the sample to be tested; in addition, the fluorescence device 602 may also include a fluorescence acquisition module to receive the fluorescence generated by the sample to be tested under the action of the excitation light. According to an embodiment of the present invention, the fluorescence device 602 may directly provide a fluorescence image of the sample to be tested to the ash analysis device 10.
[0085] In the fluorescence analyzer 60 according to an embodiment of the present invention, the fluorescence data received by the fluorescence device 602 is provided to the ash analysis device 10, and each module in the ash analysis module 10 performs data collection, screening, and calculation, and finally calculates the ash value of the sample to be tested. According to an embodiment of the present invention, since some operations in the ash analysis are migrated to the database and executed using the built-in functions of the database, the terminal device only needs to obtain the intermediate calculation results from the database and calculate the ash value of the mineral material based on the intermediate calculation results, which can significantly save the storage and computing resources of the terminal device and improve the efficiency and accuracy of the ash analysis, and the data transmission between the database and the terminal device is less. Therefore, the fluorescence analyzer provided by the present invention is particularly suitable for online use to provide an efficient, accurate, and large-capacity ash analysis solution.
[0086] The devices, mechanisms, modules, etc. described in the embodiments of the present invention may be implemented in the form of hardware, software, or a combination thereof.
[0087] The present invention can be implemented using a computer program by applying a program code to an input instruction to perform the method described herein. For the purposes of this application, a control system / module can be used to perform the method described herein, and the control system / module may include any system / module with a processor, such as, for example, a digital signal processor (DSP), a microcontroller, an application specific integrated circuit (ASIC), or a microprocessor. The program code can be implemented in a high-level procedural programming language or an object-oriented programming language to communicate with the control system / module.
[0088] One or more aspects of at least one embodiment of the invention may be implemented by representative instructions stored on a machine-readable medium that represent various logic within a processor, which when read by a machine causes the machine to fabricate logic for performing the techniques described herein.
[0089] The preferred embodiments of the present invention are described in detail above. However, it should be understood that the present invention can be implemented in various ways and variations without departing from its broad spirit and scope. A person skilled in the art can make many modifications and changes based on the concept of the present invention without creative work. Therefore, any technical solution that can be obtained by a person skilled in the art through logical analysis, reasoning or limited experiments based on the concept of the present invention on the basis of the prior art should fall within the scope of protection determined by the claims of the present invention.
Claims
1. A device for ash analysis, comprising: A data acquisition module, wherein the data acquisition module is configured to obtain a fluorescence characteristic vector of a sample to be tested; A database module, coupled to the data acquisition module, is configured to utilize a database function to: Obtaining the fluorescence characteristic vector of the sample to be tested from the data acquisition module; Searching in a database for a set of standard sample feature vectors having a similar acquisition time and the same channel address as the fluorescence feature vector of the sample to be tested, wherein the set of standard sample feature vectors includes one or more standard sample feature vectors, and the standard sample feature vectors indicate the fluorescence reaction characteristics and ash value of the standard sample; Calculating the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; and Outputting a data set to be analyzed based on the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; as well as A data analysis module is coupled to the database module and is configured to calculate the ash value of the sample to be tested based on the data set to be analyzed.
2. The device according to claim 1, in, The database module is further configured to utilize database functions to: Determining whether the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set meets a similarity standard; and In response to determining that the similarity between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the set of standard sample feature vectors satisfies a similarity criterion, the data set to be analyzed is output, wherein the data set to be analyzed indicates a subset of the set of standard sample feature vectors and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the set of standard sample feature vectors includes the standard sample feature vectors whose similarity to the fluorescence feature vector of the sample to be tested satisfies the similarity criterion, And wherein the data analysis module is configured to: The ash value of the sample to be tested is calculated based on the subset of the standard sample feature vector set and the subset similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset.
3. The device as claimed in claim 2, wherein: The database module is further configured to utilize database functions to: Sorting the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; as well as The data set to be analyzed is output based on the sorting result, wherein the subset of the standard sample feature vector set includes the first N standard sample feature vectors whose similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard, wherein N is an integer not less than 1.
4. The device according to claim 2, wherein: The calculated similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors is a first similarity calculated based on a first similarity algorithm, and wherein the database module is further configured to use a database function to perform: Calculating a second similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set based on a second similarity algorithm, wherein the second similarity algorithm is different from the first similarity algorithm; sorting the second similarities between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; and The data set to be analyzed is output based on the sorting result, wherein the subset of the standard sample feature vector set includes N standard sample feature vectors whose first similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard and whose second similarity is the highest, wherein N is an integer not less than 1.
5. The device as claimed in claim 2, in, The database module is further configured to utilize database functions to: In response to determining that the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors does not meet the similarity criterion, outputting the data set to be analyzed indicating the fluorescence feature vector of the sample to be tested, And wherein the data analysis module is configured to: Based on the fluorescence characteristic vector of the sample to be tested, the ash value of the sample to be tested is calculated according to the sample ash analysis model.
6. The device according to claim 5, wherein: The apparatus further includes a database updating module, which is coupled to the data analyzing module and is configured to: The database is updated based on the fluorescence feature vector of the sample to be tested whose similarity with each standard sample feature vector in the standard sample feature vector set is less than the similarity threshold and the calculated ash value of the sample to be tested.
7. The device of claim 1, wherein: The data acquisition module is configured to generate a fluorescence feature vector of the sample to be tested based on the fluorescence response data of a plurality of sampling points on the sample to be tested.
8. A method for ash analysis, comprising: Use database functions to: Obtaining a fluorescence characteristic vector of the sample to be tested; Searching in a database for a set of standard sample feature vectors having a similar acquisition time and the same channel address as the fluorescence feature vector of the sample to be tested, wherein the set of standard sample feature vectors includes one or more standard sample feature vectors, and the standard sample feature vectors indicate the fluorescence reaction characteristics and ash value of the standard sample; Calculating the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; and Based on the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set, outputting the data set to be analyzed, The data set to be analyzed is output to a data analysis device through the database, so that the data analysis device calculates the ash value of the sample to be tested based on the data set to be analyzed.
9. The method according to claim 8, in, Using database functions to output data sets to be analyzed includes: Determining whether the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set meets a similarity standard; and In response to determining that the similarity between the fluorescence feature vector of the sample to be tested and at least one standard sample feature vector in the set of standard sample feature vectors satisfies a similarity criterion, the data set to be analyzed is output, wherein the data set to be analyzed indicates a subset of the set of standard sample feature vectors and the similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset, and the subset of the set of standard sample feature vectors includes the standard sample feature vectors whose similarity to the fluorescence feature vector of the sample to be tested satisfies the similarity criterion, And wherein, the data analysis device calculates the ash value of the sample to be tested based on the subset of the standard sample feature vector set and the subset similarity between the fluorescence feature vector of the sample to be tested and the corresponding standard sample feature vector in the subset.
10. The method of claim 9, wherein: Using database functions to output data sets to be analyzed includes: sorting the similarities between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; and The data set to be analyzed is output based on the sorting result, wherein the subset of the standard sample feature vector set includes the first N standard sample feature vectors whose similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard, wherein N is an integer not less than 1.
11. The method of claim 9, wherein: The calculated similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the set of standard sample feature vectors is a first similarity calculated based on a first algorithm, and wherein using a database function to output the data set to be analyzed comprises: Calculating a second similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set based on a second algorithm, wherein the second algorithm is different from the first algorithm; sorting the second similarities between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set; and The data set to be analyzed is output based on the sorting result, wherein the subset of the standard sample feature vector set includes N standard sample feature vectors whose first similarity with the fluorescence feature vector of the sample to be tested meets the similarity standard and whose second similarity is the highest, wherein N is an integer not less than 1.
12. The method according to claim 9, in, Using database functions to output data sets to be analyzed includes: If the similarity between the fluorescence feature vector of the sample to be tested and each standard sample feature vector in the standard sample feature vector set does not meet the similarity criterion, outputting the data set to be analyzed indicating the fluorescence feature vector of the sample to be tested, And wherein, the data analysis device calculates the ash value of the sample to be tested based on the fluorescence feature vector of the sample to be tested and according to the sample ash analysis model.
13. The method of claim 12, wherein: The method further comprises: The database is updated based on the fluorescence feature vector of the sample to be tested whose similarity with each standard sample feature vector in the standard sample feature vector set is less than the similarity threshold and the calculated ash value of the sample to be tested.
14. An online fluorescence analyzer, comprising: A fluorescence device, the fluorescence device being configured to emit excitation light to a sample to be tested and receive a fluorescence signal from the sample to be tested; as well as A device as claimed in any one of claims 1 to 7.
15. A machine-readable medium comprising machine-readable instructions, which when executed cause a machine to perform the method according to any one of claims 8 to 13.
16. A computer program product comprising computer instructions which, when executed, cause a machine to perform the method according to any one of claims 8 to 13.
Citation Information
Patent Citations
Coal quality detection method based on image data
CN115375675A
Coal classification and recognition method and system and storage medium
CN116977729A
Coal quality analysis model training method and device, electronic equipment and storage medium
CN117216558A
Method for measuring coal ash value, ash content meter and storage medium
CN117491403A
Systems and methods for predicting sample properties based on spectral measurements
US20230194424A1
