CN115267035B - Chromatograph fault diagnosis analysis method and system - Google Patents

Chromatograph fault diagnosis analysis method and system Download PDF

Info

Publication number
CN115267035B
CN115267035B CN202211187579.8A CN202211187579A CN115267035B CN 115267035 B CN115267035 B CN 115267035B CN 202211187579 A CN202211187579 A CN 202211187579A CN 115267035 B CN115267035 B CN 115267035B
Authority
CN
China
Prior art keywords
chromatogram
analyzed
fragment
segment
similarity
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN202211187579.8A
Other languages
Chinese (zh)
Other versions
CN115267035A (en
Inventor
刘继宇
张业平
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Suzhou Innovation General Chromatography Equipment Co ltd
Original Assignee
Suzhou Innovation General Chromatography Equipment Co ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Suzhou Innovation General Chromatography Equipment Co ltd filed Critical Suzhou Innovation General Chromatography Equipment Co ltd
Priority to CN202211187579.8A priority Critical patent/CN115267035B/en
Publication of CN115267035A publication Critical patent/CN115267035A/en
Application granted granted Critical
Publication of CN115267035B publication Critical patent/CN115267035B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N30/00—Investigating or analysing materials by separation into components using adsorption, absorption or similar phenomena or using ion-exchange, e.g. chromatography or field flow fractionation
    • G01N30/02—Column chromatography
    • G01N30/86—Signal analysis
    • G01N30/8665—Signal analysis for calibrating the measuring apparatus
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V10/00—Arrangements for image or video recognition or understanding
    • G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
    • G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
    • G06V10/761—Proximity, similarity or dissimilarity measures
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V2201/00—Indexing scheme relating to image or video recognition or understanding
    • G06V2201/07—Target detection

Landscapes

  • Engineering & Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Theoretical Computer Science (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Physics & Mathematics (AREA)
  • General Health & Medical Sciences (AREA)
  • Biochemistry (AREA)
  • Databases & Information Systems (AREA)
  • Pathology (AREA)
  • Analytical Chemistry (AREA)
  • Chemical & Material Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Computing Systems (AREA)
  • Immunology (AREA)
  • Evolutionary Computation (AREA)
  • Medical Informatics (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Multimedia (AREA)
  • Other Investigation Or Analysis Of Materials By Electrical Means (AREA)

Abstract

The invention provides a chromatograph fault diagnosis analysis method and a chromatograph fault diagnosis analysis system, and relates to the technical field of data processing. In the invention, a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed are obtained, and the plurality of chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed. And for each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, performing chromatogram contrast analysis processing on the two chromatograms to be analyzed so as to output the chromatogram correlation degree between the two chromatograms to be analyzed. And according to the chromatogram correlation degree between every two chromatograms to be analyzed in the chromatograms to be analyzed, fault state determination processing is carried out on the chromatographs to be diagnosed, so that a fault state determination result corresponding to each chromatograph to be diagnosed is output and used for reflecting whether faults exist. Based on the above, the reliability of the fault diagnosis and analysis of the chromatograph can be improved to a certain extent.

Description

Chromatograph fault diagnosis analysis method and system
Technical Field
The invention relates to the technical field of data processing, in particular to a method and a system for diagnosing and analyzing a fault of a chromatograph.
Background
With the continuous maturity of data processing technology, the application range of the data processing technology is continuously expanded, for example, fault diagnosis analysis can be performed on instrument equipment based on the data processing technology, such as fault diagnosis analysis on a chromatograph. In the prior art, a chromatogram outputted by a chromatograph is generally analyzed manually to determine whether a fault exists, and manual analysis can only determine that a fault exists under the condition that the degree of deformation of a graph corresponding to the chromatogram is very large, so that the reliability is not high.
Disclosure of Invention
In view of the above, the present invention provides a method and a system for diagnosing and analyzing a chromatograph failure, so as to improve reliability of the fault diagnosis and analysis of the chromatograph to a certain extent.
In order to achieve the above purpose, the embodiment of the invention adopts the following technical scheme:
a chromatograph fault diagnosis analysis method comprising:
acquiring a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed, wherein the plurality of chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed;
for each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, performing chromatogram comparison analysis processing on the two chromatograms to be analyzed to output a chromatogram correlation degree between the two chromatograms to be analyzed, wherein the chromatogram correlation degree is used for reflecting the correlation degree between chromatographic signals;
and according to the chromatogram correlation degree between every two chromatograms to be analyzed in the chromatograms to be analyzed, performing fault state determination processing on the chromatographs to be diagnosed to output a fault state determination result corresponding to each chromatograph to be diagnosed, wherein the fault state determination result is used for reflecting whether the corresponding chromatograph to be diagnosed has a fault.
In some preferred embodiments, in the method for analyzing chromatograph fault diagnosis, the step of acquiring a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed includes:
determining a plurality of chromatographs to be diagnosed, wherein the number of the chromatographs to be diagnosed is greater than or equal to the number of preset target instruments;
for each chromatograph to be diagnosed in the plurality of chromatographs to be diagnosed, controlling the chromatograph to be diagnosed to perform detection processing on a target detection object so that the chromatograph to be diagnosed generates a corresponding chromatogram to be analyzed for the target detection object, and extracting the chromatogram to be analyzed from the chromatograph to be diagnosed after the chromatograph to be diagnosed generates the chromatogram to be analyzed.
In some preferred embodiments, in the above method for diagnosing and analyzing a chromatograph fault, the step of performing, for each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, chromatogram contrast analysis processing on the two chromatograms to be analyzed to output a chromatogram correlation degree between the two chromatograms to be analyzed includes:
carrying out any marking treatment on the two chromatograms to be analyzed so as to respectively mark and form a comparison chromatogram to be analyzed and a reference chromatogram to be analyzed;
performing spectrum segmentation operation on the chromatogram to be analyzed and the reference chromatogram to be analyzed respectively to form a chromatogram fragment sequence to be analyzed corresponding to the chromatogram to be analyzed and a chromatogram fragment sequence to be analyzed corresponding to the chromatogram to be analyzed;
for each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed, determining the graph fragment importance of the chromatogram fragment to be analyzed, and analyzing the similarity between the chromatogram fragment to be analyzed and the reference chromatogram fragment to be analyzed with the maximum similarity in the chromatogram fragment sequence to be analyzed, so as to mark the similarity as the representative similarity corresponding to the chromatogram fragment to be analyzed;
for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining the graph segment importance of the reference to-be-analyzed chromatogram segment, and analyzing the similarity between the reference to-be-analyzed chromatogram segment and the comparison to-be-analyzed chromatogram segment with the maximum similarity in the comparison to-be-analyzed chromatogram segment sequence to mark the representative similarity corresponding to the reference to-be-analyzed chromatogram segment;
analyzing and outputting the chromatogram correlation degree between the chromatogram to be analyzed and the reference chromatogram to be analyzed based on the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and the corresponding representative similarity, and combining the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and the corresponding representative similarity;
if there is no same chromatogram fragment to be analyzed between chromatogram fragment sequence portions to be analyzed corresponding to two chromatogram fragment sequences to be analyzed respectively, assigning a graph fragment importance corresponding to a chromatogram fragment to be analyzed in the two chromatogram fragment sequences to be analyzed as a difference value between a preset importance default and a graph fragment importance of the chromatogram fragment to be analyzed, wherein the two chromatogram fragment sequence portions to be analyzed are formed based on chromatogram fragments to be analyzed, which are respectively screened from the two chromatogram fragment sequences to be analyzed, of which corresponding graph fragment importance is not less than an importance reference value, the chromatogram fragment to be analyzed is a chromatogram fragment to be analyzed, which is matched with the chromatogram fragment to be analyzed with the largest similarity in the chromatogram fragment sequences to be analyzed except the chromatogram fragment sequence to be analyzed to which the chromatogram fragment to be analyzed belongs, the two chromatogram fragments to be analyzed are matched and expressed, and the similarity between the two chromatogram fragments to be analyzed is greater than or equal to the preset similarity reference value.
In some preferred embodiments, in the above method for diagnosing and analyzing a chromatograph fault, the step of analyzing and outputting the chromatogram correlation between the chromatogram to be analyzed and the reference chromatogram to be analyzed based on the graph fragment importance and the corresponding representative similarity corresponding to each chromatogram fragment to be analyzed in the sequence of chromatogram fragments to be analyzed and combining the graph fragment importance and the corresponding representative similarity corresponding to each chromatogram fragment to be analyzed in the sequence of chromatogram fragments to be analyzed includes:
performing sum value calculation on a graph fragment importance degree corresponding to each chromatogram fragment to be analyzed and a corresponding multiplication result value representing similarity included in two chromatogram fragment sequences to be analyzed so as to output a corresponding fusion calculation result value, wherein the two chromatogram fragment sequences to be analyzed include the chromatogram fragment sequence to be analyzed for comparison and the chromatogram fragment sequence to be analyzed for reference, and each chromatogram fragment to be analyzed belongs to the chromatogram fragment to be analyzed for comparison or belongs to the chromatogram fragment to be analyzed for reference;
performing sum value calculation on the importance of the map fragment corresponding to each chromatogram fragment to be analyzed included in the two chromatogram fragment sequences to be analyzed to output a corresponding importance calculation result value;
analyzing and outputting chromatogram correlation between the chromatogram to be analyzed for comparison and the chromatogram to be analyzed for reference based on the fusion calculation result value and the importance calculation result value.
In some preferred embodiments, in the above method for diagnosing and analyzing a chromatograph fault, the step of performing a sum calculation on the graph segment importance degree corresponding to each chromatogram segment to be analyzed included in the two chromatogram segment sequences to be analyzed and the corresponding multiplied result value representing the similarity to output a corresponding fused calculation result value includes:
if the same chromatogram fragment to be analyzed does not exist between the chromatogram fragment sequence portions to be analyzed corresponding to the chromatogram fragment sequences to be analyzed respectively, matching confirmation processing is carried out on each chromatogram fragment to be analyzed in the chromatogram fragment sequences to be analyzed and the chromatogram fragment to be analyzed with the maximum similarity in other chromatogram fragment sequences to be analyzed except the chromatogram fragment sequence to be analyzed to which the chromatogram fragment to be analyzed belongs, and if the matching confirmation processing result reflects that the two corresponding chromatogram fragments to be analyzed are matched, the similarity between the two chromatogram fragments to be analyzed is larger than or equal to a preset similarity reference value;
for the analyzed chromatogram segment to be analyzed which is matched with the chromatogram segment to be analyzed with the maximum similarity in other chromatogram segment sequences to be analyzed, performing difference calculation on a preset importance default and the map segment importance corresponding to the chromatogram segment to be analyzed so as to output the updated map segment importance corresponding to the chromatogram segment to be analyzed;
marking the graph fragment importance degree corresponding to the chromatogram fragment to be analyzed as the updated graph fragment importance degree corresponding to the chromatogram fragment to be analyzed aiming at the analyzed chromatogram fragment to be analyzed which is not matched with the chromatogram fragment to be analyzed with the maximum similarity in other chromatogram fragment sequences to be analyzed;
and performing sum value calculation on a multiplication result value between the importance degree of the updated map segment corresponding to each chromatogram segment to be analyzed in the two chromatogram segment sequences to be analyzed and the corresponding representative similarity so as to output a corresponding fusion calculation result value.
In some preferred embodiments, in the above method for diagnosing and analyzing a chromatograph fault, the step of, for each chromatogram segment to be analyzed in the sequence of chromatogram segments to be analyzed, determining an importance degree of the chromatogram segment to be analyzed, and analyzing a similarity between the chromatogram segment to be analyzed and a reference chromatogram segment to be analyzed having a highest similarity in the sequence of chromatogram segments to be analyzed, so as to mark a representative similarity corresponding to the chromatogram segment to be analyzed, includes:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, determining the graph segment importance degree of the chromatogram segment to be analyzed; and for each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed, determining whether a chromatogram fragment to be analyzed has a reference chromatogram fragment to be analyzed having a similar relationship with the chromatogram fragment to be analyzed according to a preset chromatogram fragment similarity relationship set, and under the condition that the chromatogram fragment to be analyzed has the reference chromatogram fragment to be analyzed having a similar relationship with the chromatogram fragment to be analyzed, marking the similarity corresponding to the similar relationship in the chromatogram fragment similarity relationship set as the representative similarity corresponding to the chromatogram fragment to be analyzed;
the step of determining the graph fragment importance of each reference chromatogram fragment to be analyzed in the reference chromatogram fragment sequence to be analyzed, analyzing the similarity between the reference chromatogram fragment to be analyzed and the comparison chromatogram fragment to be analyzed with the highest similarity in the comparison chromatogram fragment sequence to be analyzed, and marking the similarity as the representative similarity corresponding to the reference chromatogram fragment to be analyzed comprises the following steps:
determining the graph fragment importance degree of each reference chromatogram fragment to be analyzed in the reference chromatogram fragment to be analyzed sequence; and for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining whether a comparison to-be-analyzed chromatogram segment having a similar relationship with the reference to-be-analyzed chromatogram segment exists in the comparison to-be-analyzed chromatogram segment sequence according to a preset chromatogram segment similar relationship set, and under the condition that the comparison to-be-analyzed chromatogram segment having a similar relationship with the reference to-be-analyzed chromatogram segment exists in the comparison to-be-analyzed chromatogram segment sequence, marking the similarity corresponding to the similar relationship in the chromatogram segment similar relationship set as the representative similarity corresponding to the reference to-be-analyzed chromatogram segment.
In some preferred embodiments, in the above method for diagnosing and analyzing a chromatograph fault, the step of, for each chromatogram segment to be analyzed in the sequence of the chromatogram segments to be analyzed, determining a graph segment importance degree of the chromatogram segment to be analyzed, and analyzing a similarity between the chromatogram segment to be analyzed and a reference chromatogram segment to be analyzed having a highest similarity in the sequence of the chromatogram segments to be analyzed to mark a representative similarity corresponding to the chromatogram segment to be analyzed includes:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, determining the significance of the chromatogram segment to be analyzed, mining the neural network by using chromatogram features formed by network optimization, performing feature mining on the chromatogram segment to be analyzed to output the feature distribution of the chromatogram segment to be analyzed corresponding to the chromatogram segment to be analyzed, performing feature mining on each chromatogram segment to be analyzed included in the chromatogram segment sequence to be analyzed to output the feature distribution of the chromatogram segment to be analyzed corresponding to each chromatogram segment to be analyzed, calculating the feature distribution similarity between the chromatogram segment to be analyzed and each chromatogram segment to be analyzed, and marking the feature distribution similarity with the maximum value as the representative similarity corresponding to the chromatogram segment to be analyzed;
the step of determining the graph fragment importance of each reference chromatogram fragment to be analyzed in the reference chromatogram fragment sequence to be analyzed, analyzing the similarity between the reference chromatogram fragment to be analyzed and the comparison chromatogram fragment to be analyzed with the highest similarity in the comparison chromatogram fragment sequence to be analyzed, and marking the similarity as the representative similarity corresponding to the reference chromatogram fragment to be analyzed comprises the following steps:
for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining the graph segment importance of the reference to-be-analyzed chromatogram segment, mining a neural network by utilizing chromatogram features formed by network optimization, performing feature mining processing on the reference to-be-analyzed chromatogram segment to output the feature distribution of the reference to-be-analyzed chromatogram segment corresponding to the reference to-be-analyzed chromatogram segment, performing feature mining processing on each comparison to-be-analyzed chromatogram segment included in the comparison to-be-analyzed chromatogram segment sequence to output the feature distribution of the comparison to-be-analyzed chromatogram segment corresponding to each comparison to-be-analyzed chromatogram segment, calculating the feature distribution similarity between the feature distribution of the reference to-be-analyzed chromatogram segment and the feature distribution of each comparison to-be-analyzed chromatogram segment, and marking the feature distribution similarity with the maximum value as the representative similarity corresponding to the reference to-analyzed chromatogram segment.
In some preferred embodiments, in the above method for diagnosing and analyzing a chromatograph fault, the step of determining, for each chromatogram segment to be analyzed in the sequence of the chromatogram segments to be analyzed, a graph segment importance degree of the chromatogram segment to be analyzed includes:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, respectively calculating the similarity between the chromatogram segment to be analyzed and each target chromatogram segment in a preset target chromatogram segment set, and analyzing the graph segment importance of the chromatogram segment to be analyzed based on the similarity and the segment importance preset for each target chromatogram segment;
the step of determining the map segment importance of each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence comprises the following steps:
for each reference chromatogram segment to be analyzed in the reference chromatogram segment sequence to be analyzed, respectively calculating the similarity between the reference chromatogram segment to be analyzed and each target chromatogram segment in a preset target chromatogram segment set, and analyzing the graph segment importance of the reference chromatogram segment to be analyzed based on the similarity and the segment importance preset for each target chromatogram segment.
In some preferred embodiments, in the above chromatograph fault diagnosis analysis method, the step of performing fault state determination processing on the plurality of chromatographs to be diagnosed according to a chromatogram correlation between each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed to output a fault state determination result corresponding to each chromatograph to be diagnosed includes:
for each chromatogram to be analyzed in the plurality of chromatograms to be analyzed, performing mean value calculation on the chromatogram correlation degree between the chromatogram to be analyzed and each other chromatogram to be analyzed except the chromatogram to be analyzed so as to output a representative chromatogram correlation degree corresponding to the chromatogram to be analyzed;
for each chromatogram to be analyzed in the plurality of chromatograms to be analyzed, comparing the correlation degree of the representative chromatogram corresponding to the chromatogram to be analyzed with a preset first chromatogram correlation degree reference value, and marking the chromatogram to be analyzed as the first chromatogram to be analyzed when the correlation degree of the representative chromatogram corresponding to the chromatogram to be analyzed is smaller than the first chromatogram correlation degree reference value;
classifying the plurality of chromatograms to be analyzed according to the chromatogram correlation degree between every two chromatograms to be analyzed in the plurality of chromatograms to be analyzed to form at least one chromatogram classification set corresponding to the plurality of chromatograms to be analyzed, wherein each chromatogram classification set comprises at least one chromatogram to be analyzed, and for each chromatogram classification set comprising the plurality of chromatograms to be analyzed, the chromatogram correlation degree between any two chromatograms to be analyzed in the chromatogram classification set is greater than or equal to a second preset chromatogram correlation degree reference value;
for each chromatogram classification set, when the number of chromatograms to be analyzed in the chromatogram classification set is less than or equal to a preset chromatogram number reference value, marking a fault state determination result of a chromatograph to be diagnosed corresponding to a first chromatogram to be analyzed included in the chromatogram classification set as a first fault state determination result, and marking a fault state determination result of a chromatograph to be diagnosed corresponding to other chromatograms to be analyzed except for the first chromatogram to be analyzed included in the chromatogram classification set as a second fault state determination result, or when the number of chromatograms to be analyzed included in the chromatogram classification set is greater than the chromatogram number reference value, marking a fault state determination result of a chromatograph to be diagnosed corresponding to each chromatogram to be analyzed included in the chromatogram classification set as a second fault state determination result, wherein the first fault state determination result is used for reflecting that the corresponding chromatograph to be diagnosed has a fault, and the second fault state determination result is used for reflecting that the chromatograph to be diagnosed does not have a fault.
The embodiment of the present invention further provides a chromatograph fault diagnosis analysis system, which includes a processor and a memory, where the memory is used to store a computer program, and the processor is used to execute the computer program, so as to implement the above chromatograph fault diagnosis analysis method.
The chromatograph fault diagnosis and analysis method and system provided by the embodiment of the invention can be used for obtaining a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed. And for each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, performing chromatogram contrast analysis processing on the two chromatograms to be analyzed so as to output the chromatogram correlation degree between the two chromatograms to be analyzed. And performing fault state determination processing on the plurality of chromatographs to be diagnosed according to the chromatogram correlation degree between every two chromatograms to be analyzed in the plurality of chromatograms to be analyzed so as to output a fault state determination result corresponding to each chromatograph to be diagnosed. Based on this, because the plurality of chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed, the chromatograms to be analyzed should have higher correlation when the chromatographs to be diagnosed have no fault, and therefore, the fault state determination result corresponding to each chromatograph to be diagnosed can be reliably determined based on the chromatogram correlation between every two chromatograms to be analyzed, so that the reliability of fault diagnosis and analysis of the chromatographs is improved to a certain extent, and the defects of the prior art are overcome.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
Fig. 1 is a block diagram of a chromatograph fault diagnosis analysis system according to an embodiment of the present invention.
Fig. 2 is a schematic flowchart of steps included in a chromatograph fault diagnosis analysis method according to an embodiment of the present invention.
Fig. 3 is a schematic diagram of modules included in a chromatograph fault diagnosis analysis apparatus according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. The components of embodiments of the present invention generally described and illustrated in the figures herein may be arranged and designed in a wide variety of different configurations. Thus, the following detailed description of the embodiments of the present invention, as presented in the figures, is not intended to limit the scope of the invention, as claimed, but is merely representative of selected embodiments of the invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a chromatograph fault diagnosis analysis system. Wherein the chromatograph fault diagnosis analysis system may include a memory and a processor.
It will be appreciated that in some embodiments, the memory and processor are in direct or indirect electrical communication to enable the transfer or interaction of data. For example, they may be electrically connected to each other via one or more communication buses or signal lines. The memory can have stored therein at least one software function (computer program) which can be present in the form of software or firmware. The processor may be configured to execute the executable computer program stored in the memory, thereby implementing a chromatograph fault diagnosis analysis method provided by an embodiment of the present invention (described below).
It should be appreciated that in some embodiments, the Memory may be, but is not limited to, random Access Memory (RAM), read Only Memory (ROM), programmable Read-Only Memory (PROM), erasable Read-Only Memory (EPROM), electrically Erasable Read-Only Memory (EEPROM), and the like. The Processor may be a general-purpose Processor, including a Central Processing Unit (CPU), a Network Processor (NP), a System on Chip (SoC), and the like; but may also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other programmable logic device, discrete gate or transistor logic, discrete hardware components.
It should be appreciated that in some embodiments, the chromatograph fault diagnosis analysis system may be a server with data processing capabilities.
With reference to fig. 2, an embodiment of the present invention further provides a method for diagnosing and analyzing a chromatograph fault, which can be applied to the system for diagnosing and analyzing a chromatograph fault. The method steps defined by the related flow of the chromatograph fault diagnosis and analysis method can be realized by the chromatograph fault diagnosis and analysis system.
The specific process shown in fig. 2 will be described in detail below.
Step S110, a plurality of chromatograms to be analyzed corresponding to the plurality of chromatographs to be diagnosed are obtained.
In the embodiment of the invention, the chromatograph fault diagnosis analysis system can acquire a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed. The chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed (for example, the detection of the same target detection object by the plurality of chromatographs to be diagnosed may refer to the detection of one target detection object by the plurality of chromatographs to be diagnosed sequentially, or may refer to the detection of the plurality of chromatographs to be diagnosed respectively on the plurality of target detection objects related thereto).
Step S120, for each two to-be-analyzed chromatograms in the multiple to-be-analyzed chromatograms, performing chromatogram comparison analysis processing on the two to-be-analyzed chromatograms, so as to output a chromatogram correlation degree between the two to-be-analyzed chromatograms.
In the embodiment of the present invention, the chromatograph fault diagnosis and analysis system may perform chromatogram comparison analysis processing on each two to-be-analyzed chromatograms in the plurality of to-be-analyzed chromatograms, so as to output a chromatogram correlation degree between the two to-be-analyzed chromatograms. The chromatogram correlation is used to reflect the degree of correlation between chromatographic signals.
Step S130, performing fault status determination processing on the plurality of chromatographs to be diagnosed according to the chromatogram correlation between every two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, so as to output a fault status determination result corresponding to each chromatograph to be diagnosed.
In this embodiment of the present invention, the chromatograph fault diagnosis analysis system may perform fault state determination processing on the plurality of chromatographs to be diagnosed according to a chromatogram correlation degree between every two chromatograms to be analyzed, so as to output a fault state determination result corresponding to each chromatograph to be diagnosed. The fault state determination result is used for reflecting whether the corresponding chromatograph to be diagnosed has a fault (i.e. has a fault or does not have a fault).
Based on this, because the plurality of chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed, the chromatograms to be analyzed should have a higher degree of correlation when the chromatographs to be diagnosed are not in fault, and therefore, the fault state determination result corresponding to each chromatograph to be diagnosed can be reliably determined based on the degree of correlation of the chromatograms between every two chromatograms to be analyzed, so that the reliability of fault diagnosis and analysis of the chromatographs is improved to a certain extent, and the defects of the prior art are overcome.
It should be understood that, in some embodiments, step S110 described above may include:
determining a plurality of chromatographs to be diagnosed, wherein the number of the chromatographs to be diagnosed is greater than or equal to the number of target instruments configured in advance (the specific numerical value of the number of the target instruments can be configured according to the actual application requirements, such as 10, 15, 20, etc.);
for each chromatograph to be diagnosed in the plurality of chromatographs to be diagnosed, controlling the chromatograph to be diagnosed to perform detection processing on a target detection object so that the chromatograph to be diagnosed generates a corresponding chromatogram to be analyzed for the target detection object, and extracting the chromatogram to be analyzed from the chromatograph to be diagnosed after the chromatograph to be diagnosed generates the chromatogram to be analyzed.
It should be understood that, in some embodiments, step S120 described above may include (it should be noted that the following steps are only for two of them, and other references apply):
performing any labeling processing on the two chromatograms to be analyzed to form a chromatogram to be analyzed for comparison and a chromatogram to be analyzed for reference (that is, any one chromatogram to be analyzed can be labeled as a chromatogram to be analyzed for comparison, and the other chromatogram is labeled as a chromatogram to be analyzed for reference, it should be noted that "comparison" and "reference" in the chromatogram to be analyzed for comparison and the chromatogram to be analyzed for reference do not have specific meanings, but are only used for distinguishing and describing the two chromatograms to be analyzed in the process of performing chromatogram comparison and analysis processing on the two chromatograms to be analyzed, for example, the chromatogram to be analyzed for comparison can refer to the first chromatogram to be analyzed in the two chromatograms, and the chromatogram to be analyzed for reference can refer to the second chromatogram to be analyzed in the two chromatograms);
performing map segmentation operation on the chromatogram to be analyzed and the reference chromatogram to be analyzed respectively to form a chromatogram fragment sequence to be analyzed corresponding to the chromatogram to be analyzed and a chromatogram fragment sequence to be analyzed corresponding to the chromatogram to be analyzed (for example, the chromatogram fragment sequence to be analyzed may include a plurality of chromatogram fragments to be analyzed, and the chromatogram fragment sequence to be analyzed may include a plurality of chromatogram fragments to be analyzed);
for each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed, determining the graph fragment importance degree of the chromatogram fragment to be analyzed, and analyzing the similarity between the chromatogram fragment to be analyzed and the reference chromatogram fragment to be analyzed with the highest similarity in the chromatogram fragment sequence to be analyzed, so as to mark the representative similarity corresponding to the chromatogram fragment to be analyzed (illustratively, for the chromatogram fragment F1 to be analyzed in the chromatogram fragment sequence to be analyzed, obtaining the graph fragment importance degree W1 corresponding to F1, and determining the similarity between the chromatogram fragment to be analyzed H1 and the reference chromatogram fragment to be analyzed H2, the chromatogram fragment to be analyzed H2, 8230, the chromatogram fragment to be analyzed with the highest similarity in the chromatogram fragment to be analyzed Hn, for example, the similarity between the chromatogram fragment Hn 1 and the reference fragment to be analyzed with the highest similarity in the chromatogram fragment to be analyzed, and the similarity between the F1 and the fragment sequence to be analyzed is taken as the similarity between the F1 and the reference fragment to be analyzed, namely the representative similarity between the fragment to be analyzed and the reference chromatogram fragment to be analyzed;
for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining a graph segment importance degree of the reference to-be-analyzed chromatogram segment, and analyzing a similarity between the reference to-be-analyzed chromatogram segment and a comparison to-be-analyzed chromatogram segment with the highest similarity in the comparison to-be-analyzed chromatogram segment sequence, so as to mark the similarity as a representative similarity corresponding to the reference to-be-analyzed chromatogram segment (illustratively, for a reference to-be-analyzed chromatogram segment H1 in the reference to-be-analyzed chromatogram segment sequence, obtaining a graph segment importance degree Z1 corresponding to H1, and determining a similarity between H1 and the comparison to-be-analyzed chromatogram segment F1, the comparison to-be-analyzed chromatogram segment F2, 8230, a similarity between H1 and the comparison to-analyzed chromatogram segment Fn with the highest similarity, for example, a similarity between H1 and the comparison to-be-analyzed chromatogram segment Fn included in the comparison to-be-analyzed chromatogram segment Fn is the highest, and then taking the similarity between H1 and the comparison to-analyzed chromatogram segment Fn as a similarity between H1 and the comparison to-analyzed chromatogram segment Fn, that is the representative similarity;
analyzing and outputting the chromatogram correlation degree between the chromatogram to be analyzed and the reference chromatogram to be analyzed based on the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and the corresponding representative similarity, and combining the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and the corresponding representative similarity.
It should be understood that, in some embodiments, the performing, for the above-mentioned map segmentation operation on the chromatogram to be analyzed by comparison and the chromatogram to be analyzed by reference to form a chromatogram fragment sequence to be analyzed by comparison corresponding to the chromatogram to be analyzed by comparison and a chromatogram fragment sequence to be analyzed by reference corresponding to the chromatogram to be analyzed by reference may include:
according to the current assignment of the length of the first fragment (which can be any length), carrying out segmentation processing on the chromatogram to be analyzed for comparison to form an initial chromatogram fragment sequence to be analyzed for comparison corresponding to the chromatogram to be analyzed for comparison, and then according to the preset length of the first fragment, carrying out segmentation processing on the chromatogram to be analyzed for reference to form an initial chromatogram fragment sequence to be analyzed for reference corresponding to the chromatogram to be analyzed;
for each initial comparison chromatogram fragment to be analyzed in the initial comparison chromatogram fragment sequence to be analyzed, calculating a difference initial comparison chromatogram fragment to be analyzed between the initial comparison chromatogram fragment to be analyzed and each preceding initial comparison chromatogram fragment to be analyzed in front of the initial comparison chromatogram fragment to be analyzed, and then performing mean value fusion processing on the difference initial comparison chromatogram fragment to be analyzed to form a representative difference initial comparison chromatogram fragment to be analyzed corresponding to the initial comparison chromatogram fragment to be analyzed (exemplarily, the preceding initial comparison chromatogram fragment to be analyzed corresponding to the first initial comparison chromatogram fragment to be analyzed is the first initial comparison chromatogram fragment to be analyzed, that is, in the initial comparison chromatogram fragment sequence to be analyzed, because there are no other initial comparison chromatogram fragments to be analyzed in front of the first initial comparison chromatogram fragment to be analyzed, the first initial comparison chromatogram fragment to be analyzed is taken as the corresponding preceding initial comparison chromatogram fragment to be analyzed; for each other initial comparison chromatogram fragments to be analyzed except for the first initial comparison chromatogram fragment to be analyzed in the initial comparison chromatogram fragment sequence to be analyzed, taking each initial comparison chromatogram fragment to be analyzed in front of the other initial comparison chromatogram fragments to be analyzed as a preceding initial comparison chromatogram fragment to be analyzed corresponding to the other initial comparison chromatogram fragments to be analyzed, and then performing difference calculation on the initial comparison chromatogram fragments to be analyzed and the corresponding preceding initial comparison chromatogram fragments to be analyzed to obtain corresponding difference value initial comparison chromatogram fragments to be analyzed, in addition, the difference calculation of the initial comparison chromatogram segments to be analyzed may refer to difference calculation of corresponding waveforms, for example, the lengths of the initial comparison chromatogram segments to be analyzed are all the same, so as to align the initial comparison chromatogram segments to be analyzed according to a time axis in the waveform diagram, and then calculate the difference. For example, the initial comparison to-be-analyzed chromatogram fragment sequence includes fragment 1, fragment 2, fragment 3, and fragment 4, for fragment 1, difference calculation may be performed on fragment 1 and fragment 1 to obtain a difference initial comparison to-be-analyzed chromatogram fragment, for fragment 2, difference calculation may be performed on fragment 2 and fragment 1 to obtain a difference initial comparison to-be-analyzed chromatogram fragment, for fragment 3, difference calculation may be performed on fragment 3 and fragment 1, difference calculation may be performed on fragment 3 and fragment 2 to obtain two difference initial comparison to-be-analyzed chromatogram fragments, for fragment 4, difference calculation may be performed on fragment 4 and fragment 3, difference calculation may be performed on fragment 4 and fragment 2, and difference calculation may be performed on fragment 4 and fragment 1 to obtain three difference initial comparison to-be-analyzed chromatogram fragments);
for each initial reference chromatogram fragment to be analyzed in the initial reference chromatogram fragment sequence to be analyzed, calculating a difference initial reference chromatogram fragment to be analyzed between the initial reference chromatogram fragment to be analyzed and each preceding initial reference chromatogram fragment to be analyzed in front of the initial reference chromatogram fragment to be analyzed, and then performing mean value fusion processing on the difference initial reference chromatogram fragment to be analyzed to form a representative difference initial reference chromatogram fragment to be analyzed corresponding to the initial reference chromatogram fragment to be analyzed (exemplarily, a preceding initial reference chromatogram fragment to be analyzed corresponding to a first initial reference chromatogram fragment to be analyzed is the first initial reference chromatogram fragment to be analyzed);
for each initial comparison to-be-analyzed chromatogram segment in the initial comparison to-be-analyzed chromatogram segment sequence, performing energy value calculation on a representative difference value initial comparison to-be-analyzed chromatogram segment corresponding to the initial comparison to-be-analyzed chromatogram segment to output a map segment energy value corresponding to the initial comparison to-be-analyzed chromatogram segment (illustratively, wave energy calculation can be performed on a specific map waveform of the representative difference value initial comparison to-be-analyzed chromatogram segment, a specific technical manner can refer to related prior art, and is not specifically limited herein);
for each initial reference to-be-analyzed chromatogram segment in the initial reference to-be-analyzed chromatogram segment sequence, performing energy value calculation on a representative difference initial reference to-be-analyzed chromatogram segment corresponding to the initial reference to-be-analyzed chromatogram segment to output a map segment energy value corresponding to the initial reference to-be-analyzed chromatogram segment (for example, wave energy calculation may be performed on a specific map waveform of the representative difference initial reference to-be-analyzed chromatogram segment);
performing mean calculation and dispersion calculation on an image fragment energy value corresponding to each initial chromatogram fragment to be analyzed in the initial comparison chromatogram fragment sequence to be analyzed and an image fragment energy value corresponding to each initial reference chromatogram fragment to be analyzed in the initial reference chromatogram fragment sequence to determine a corresponding image fragment energy mean value and a corresponding image fragment energy dispersion, and determining a first screening coefficient based on the image fragment energy mean value, determining a second screening coefficient based on the image fragment energy dispersion, and determining a third screening coefficient based on the first fragment length, and performing fusion processing on the first screening coefficient, the second screening coefficient, and the third screening coefficient to output a corresponding fusion screening coefficient (illustratively, there may be a positive correlation correspondence between the image fragment energy mean value and the first screening coefficient, there may be a negative correlation correspondence between the image fragment energy degree and the second screening coefficient, and there may be a negative correlation correspondence between the first fragment length and the third screening coefficient);
after the first fragment length is subjected to multiple assignments and a fusion screening coefficient corresponding to each assignment is obtained, the fusion screening coefficient with the maximum value is determined to serve as a target fusion screening coefficient, an initial comparison chromatogram fragment sequence to be analyzed (an initial comparison chromatogram fragment sequence to be analyzed obtained by performing segmentation processing based on the assignments) corresponding to the assignment corresponding to the target fusion screening coefficient is marked as a comparison chromatogram fragment sequence to be analyzed corresponding to the comparison chromatogram to be analyzed, and an initial reference chromatogram fragment sequence to be analyzed (an initial reference chromatogram fragment sequence to be analyzed obtained by performing segmentation processing based on the assignments) corresponding to the assignment corresponding to the target fusion screening coefficient is marked as a reference chromatogram fragment sequence to be analyzed corresponding to the reference chromatogram to be analyzed.
It should be understood that, in some embodiments, for each of the chromatogram segments to be analyzed for comparison in the chromatogram segment sequence to be analyzed for comparison, the step of determining the graph segment importance degree of the chromatogram segment to be analyzed for comparison, and analyzing the similarity between the chromatogram segment to be analyzed for comparison and the chromatogram segment to be analyzed for reference with the largest similarity in the chromatogram segment sequence to be analyzed for reference, so as to mark the representative similarity corresponding to the chromatogram segment to be analyzed for comparison, may include:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, determining the graph segment importance of the chromatogram segment to be analyzed; and for each chromatogram fragment to be analyzed in the chromatogram fragment sequences to be analyzed, determining whether a chromatogram fragment to be analyzed to be compared has a reference chromatogram fragment to be analyzed with a similar relationship to the chromatogram fragment to be analyzed according to a preset chromatogram fragment similar relationship set (at least one similar relationship is included in the chromatogram fragment similar relationship set, such as that the chromatogram fragment a is similar to the chromatogram fragment B, and thus, if the chromatogram fragment to be analyzed is the chromatogram fragment a, it is required to determine whether the chromatogram fragment sequence to be analyzed has the chromatogram fragment B), and, in the case that the chromatogram fragment to be analyzed to be referred has a reference chromatogram fragment to be analyzed with a similar relationship to the chromatogram fragment to be analyzed, calculating a similarity corresponding to the similar relationship in the fragment similar relationship set (such as the similarity between the chromatogram fragment a and the fragment B, which can be labeled or calculated in advance, that the similarity between signal waveforms in the chromatogram is calculated, and can be labeled as a correlation technique for referring to the trajectory similarity), as a corresponding representative similarity of the chromatogram fragment to be analyzed.
It should be understood that, in some embodiments, for each of the chromatogram fragment to be analyzed for reference in the chromatogram fragment sequence to be analyzed described above, the step of determining the graph fragment importance of the chromatogram fragment to be analyzed for reference, and analyzing the similarity between the chromatogram fragment to be analyzed for reference and the chromatogram fragment to be analyzed for comparison with the highest similarity in the chromatogram fragment sequence to be analyzed for comparison, so as to mark the representative similarity corresponding to the chromatogram fragment to be analyzed for reference, may include:
determining the graph fragment importance degree of each reference chromatogram fragment to be analyzed in the reference chromatogram fragment sequence to be analyzed; and for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining whether a comparison to-be-analyzed chromatogram segment having a similar relationship with the reference to-be-analyzed chromatogram segment exists in the comparison to-be-analyzed chromatogram segment sequence according to a preset chromatogram segment similarity relationship set, and under the condition that the comparison to-be-analyzed chromatogram segment having a similar relationship with the reference to-be-analyzed chromatogram segment exists in the comparison to-be-analyzed chromatogram segment sequence, marking the similarity corresponding to the similar relationship in the chromatogram segment similarity relationship set as the representative similarity corresponding to the reference to-be-analyzed chromatogram segment (refer to the related description above).
It should be understood that, in other embodiments, for each of the chromatogram segments to be analyzed for comparison in the chromatogram segment sequence to be analyzed, the step of determining the significance of the chromatogram segment to be analyzed for comparison, and analyzing the similarity between the chromatogram segment to be analyzed for comparison and the chromatogram segment to be analyzed for reference with the highest similarity in the chromatogram segment sequence to be analyzed for reference, to mark the representative similarity corresponding to the chromatogram segment to be analyzed for comparison, may include:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, determining the graph segment importance degree of the chromatogram segment to be analyzed, performing feature mining on the chromatogram segment to be analyzed by utilizing a chromatogram feature mining neural network formed by network optimization to output the chromatogram segment feature distribution to be analyzed corresponding to the chromatogram segment to be analyzed, performing feature mining on each chromatogram segment to be analyzed included in the chromatogram segment sequence to be analyzed to output the chromatogram segment feature distribution to be analyzed corresponding to each chromatogram segment to be analyzed, calculating the feature distribution similarity between the chromatogram segment feature distribution to be analyzed and each chromatogram segment to be analyzed, and, the feature distribution similarity with the maximum value is marked as a representative similarity corresponding to the chromatogram segment to be analyzed (for example, the chromatogram feature mining neural network may be a coding network, so as to perform coding processing on the chromatogram segment to be analyzed and the chromatogram segment to be analyzed respectively, so as to obtain the corresponding chromatogram segment feature distribution to be analyzed and the corresponding chromatogram segment feature distribution to be analyzed, where the coding network may be any existing coding network, such as a sparse self-coding network, a noise reduction self-coding network, a contraction self-coding network, a stacking self-coding network, a depth self-coding network, and the like, and the specific processing procedures thereof may refer to related existing technologies, and are not particularly limited herein, as long as the chromatogram segment to be analyzed and the chromatogram segment to be analyzed can be mapped to a vector space, so as to obtain corresponding chromatogram segment feature vectors to be analyzed and corresponding chromatogram segment feature vectors to be analyzed, namely chromatogram segment feature distribution to be analyzed and chromatogram segment feature distribution to be analyzed; in addition, calculating the feature distribution similarity may refer to calculating a product between feature distributions).
It should be understood that, in other embodiments, for each of the chromatogram fragment to be analyzed for reference in the chromatogram fragment sequence to be analyzed described above, the step of determining the graph fragment importance of the chromatogram fragment to be analyzed for reference, and analyzing the similarity between the chromatogram fragment to be analyzed for reference and the chromatogram fragment to be analyzed for comparison with the highest similarity in the chromatogram fragment sequence to be analyzed for comparison, so as to mark the representative similarity corresponding to the chromatogram fragment to be analyzed for reference, may include:
for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining a chromatogram segment importance of the reference to-be-analyzed chromatogram segment, mining a neural network by using chromatogram features formed by network optimization, performing feature mining on the reference to-be-analyzed chromatogram segment to output a reference to-be-analyzed chromatogram segment feature distribution corresponding to the reference to-be-analyzed chromatogram segment, performing feature mining on each comparison to-be-analyzed chromatogram segment included in the comparison to-be-analyzed chromatogram segment sequence to output a comparison to-be-analyzed chromatogram segment feature distribution corresponding to each comparison to-be-analyzed chromatogram segment, calculating a feature distribution similarity between the reference to-be-analyzed chromatogram segment feature distribution and each comparison to-be-analyzed chromatogram segment feature distribution, and marking the feature distribution similarity with a maximum value as a representative similarity corresponding to the reference to-analyzed chromatogram segment (refer to the above-mentioned correlation description).
It should be understood that, in some embodiments, for each chromatogram fragment to be analyzed in the above-mentioned comparison of the sequences of the chromatogram fragments to be analyzed, the step of determining the importance of the chromatogram fragment to be analyzed may include:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, calculating a similarity between the chromatogram segment to be analyzed and each target chromatogram segment in a preset target chromatogram segment set, and then, based on the similarity and a segment importance preset for each chromatogram segment (which may be used to reflect an importance degree of the target chromatogram segment), analyzing an image segment importance degree of the chromatogram segment to be analyzed (for example, the similarity may be used as a weighting coefficient, and the segment importance degree is subjected to weighted summation calculation to obtain the image segment importance degree of the chromatogram segment to be analyzed, for example, each chromatogram segment to be analyzed may be a chromatogram segment selected manually, and a corresponding segment importance degree is generated manually based on the chromatogram segment importance degree, for example, a corresponding segment importance degree may be determined according to a waveform of the target chromatogram segment, such as a segment importance degree of a waveform a may be greater than a segment importance degree of a waveform B, for example, a waveform of a steep waveform of the chromatogram segment may be greater than a target importance degree of a target chromatogram segment, and a target chromatogram segment importance degree is greater than a target chromatogram segment of a waveform.
It should be understood that, in some embodiments, for each reference chromatogram segment to be analyzed in the reference chromatogram segment sequence to be analyzed, the step of determining the graph segment importance of the reference chromatogram segment to be analyzed may include:
for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, respectively calculating the similarity between the reference to-be-analyzed chromatogram segment and each target chromatogram segment in a preset target chromatogram segment set, and analyzing the graph segment importance of the reference to-be-analyzed chromatogram segment based on the similarity and the segment importance preset for each target chromatogram segment (refer to the above-mentioned related description).
It should be understood that, in some embodiments, based on the above-mentioned manner of determining the importance of the chromatogram segments to be analyzed, for example, if there is no identical chromatogram segment to be analyzed between the chromatogram segment sequence portions to be analyzed corresponding to the two chromatogram segment sequences to be analyzed, the importance of the chromatogram segment to be analyzed corresponding to the target chromatogram segment to be analyzed in the two chromatogram segment sequences to be analyzed is assigned as a default value of preset importance (for example, the default value of importance may be 1) and the difference value between the importance of the chromatogram segment to be analyzed (i.e., the importance of the chromatogram segment determined by the aforementioned determining manner) of the chromatogram segment to be analyzed and the importance of the chromatogram segment to be analyzed (for example, the specific value of the importance reference value may be, for example, 0.7 or the like) of the chromatogram segment to be analyzed, which the importance is not less than the chromatogram reference value of the chromatogram segment to be analyzed screened out of the two chromatogram segment sequences to be analyzed, the target chromatogram segment to be analyzed is assigned as a chromatogram segment to be analyzed, which is not less than the chromatogram reference value of the similarity of the chromatogram segment to be analyzed, which is equal to the chromatogram segment to be analyzed, or which is greater than the similarity of the chromatogram segment to be analyzed in the chromatogram segment to be analyzed, which is matched with the chromatogram segment to be analyzed, for example, 9.
It should be understood that, in some embodiments, for the step of analyzing and outputting the chromatogram correlation between the chromatogram to be analyzed by comparing and the chromatogram to be analyzed based on the graph fragment importance degree and the corresponding representative similarity corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and combining the graph fragment importance degree and the corresponding representative similarity corresponding to each chromatogram fragment to be analyzed in the reference chromatogram fragment sequence to be analyzed, the method may include:
performing sum value calculation on a graph fragment importance degree corresponding to each chromatogram fragment to be analyzed and a corresponding multiplication result value representing the similarity included in the two chromatogram fragment sequences to be analyzed to output a corresponding fusion calculation result value (that is, for each chromatogram fragment to be analyzed, multiplying the graph fragment importance degree corresponding to the chromatogram fragment to be analyzed and the corresponding representation similarity to obtain a corresponding multiplication result value, and then performing sum value calculation on the multiplication result value corresponding to each chromatogram fragment to be analyzed to output a corresponding fusion calculation result value), wherein the two chromatogram fragment sequences to be analyzed include the comparison chromatogram fragment sequence to be analyzed and the reference chromatogram fragment sequence to be analyzed, and each chromatogram fragment to be analyzed belongs to the comparison chromatogram fragment to be analyzed or belongs to the reference chromatogram fragment to be analyzed;
performing sum value calculation on the importance of the map fragment corresponding to each chromatogram fragment to be analyzed included in the two chromatogram fragment sequences to be analyzed to output a corresponding importance calculation result value;
the chromatogram correlation between the chromatogram to be analyzed for comparison and the chromatogram to be analyzed for reference is analyzed and output based on the fusion calculation result value and the importance calculation result value (illustratively, a quotient calculation may be performed on the fusion calculation result value and the importance calculation result value, that is, the former is divided by the latter to take the quotient calculation result as the chromatogram correlation).
It should be understood that, in some embodiments, the above-mentioned step of performing a sum value calculation on the graph fragment importance degree corresponding to each of the chromatogram fragment to be analyzed included in the two chromatogram fragment sequences to be analyzed and the corresponding multiplied result value representing the similarity to output a corresponding fusion calculation result value may include:
if the parts of the chromatogram fragment sequences to be analyzed corresponding to the chromatogram fragment sequences to be analyzed respectively do not have the same chromatogram fragment to be analyzed, matching confirmation processing is carried out on each chromatogram fragment to be analyzed in the two chromatogram fragment sequences to be analyzed and the chromatogram fragment to be analyzed with the highest similarity in the chromatogram fragment sequences to be analyzed except the chromatogram fragment sequence to be analyzed to which the chromatogram fragment to be analyzed belongs, and if the matching confirmation processing result reflects that the two corresponding chromatogram fragments to be analyzed are matched, the similarity between the two chromatogram fragments to be analyzed is larger than or equal to a preset similarity reference value; for the analyzed chromatogram segment to be analyzed which is matched with the chromatogram segment to be analyzed with the maximum similarity in other chromatogram segment sequences to be analyzed, performing difference calculation on a preset importance default and the map segment importance corresponding to the chromatogram segment to be analyzed to output the updated map segment importance corresponding to the chromatogram segment to be analyzed (namely taking the difference as the updated map segment importance); marking the graph fragment importance degree corresponding to the chromatogram fragment to be analyzed as the updated graph fragment importance degree corresponding to the chromatogram fragment to be analyzed aiming at the analyzed chromatogram fragment to be analyzed which is not matched with the chromatogram fragment to be analyzed with the maximum similarity in other chromatogram fragment sequences to be analyzed; and performing sum value calculation on a multiplication result value between the importance degree of the updated chromatogram segment corresponding to each chromatogram segment to be analyzed in the two chromatogram segment sequences to be analyzed and the corresponding representative similarity so as to output a corresponding fusion calculation result value.
It should be understood that, in some embodiments, for the step S130 described above, the following steps may be included:
for each chromatogram to be analyzed in the plurality of chromatograms to be analyzed, performing mean value calculation on the chromatogram correlation degree between the chromatogram to be analyzed and each other chromatogram to be analyzed except the chromatogram to be analyzed so as to output a representative chromatogram correlation degree corresponding to the chromatogram to be analyzed;
for each chromatogram to be analyzed in the plurality of chromatograms to be analyzed, comparing the correlation degree of the representative chromatogram corresponding to the chromatogram to be analyzed with a preset first chromatogram correlation degree reference value, and labeling the chromatogram to be analyzed as a first chromatogram to be analyzed when the correlation degree of the representative chromatogram corresponding to the chromatogram to be analyzed is smaller than the first chromatogram correlation degree reference value (for example, the fault state determination result of the chromatograph to be diagnosed corresponding to the first chromatogram to be analyzed may also be directly labeled as a first fault state determination result);
classifying the plurality of chromatograms to be analyzed according to the chromatogram correlation between each two chromatograms to be analyzed in the plurality of chromatograms to form at least one chromatogram classification set corresponding to the plurality of chromatograms to be analyzed, where each chromatogram classification set includes at least one chromatogram to be analyzed, and for each chromatogram classification set including the plurality of chromatograms to be analyzed, the chromatogram correlation between any two chromatograms to be analyzed in the chromatogram classification set is greater than or equal to a pre-configured second chromatogram correlation reference value (for example, the relative size relationship between the second chromatogram correlation reference value and the first chromatogram correlation reference value is not limited, for example, the second chromatogram correlation reference value may be greater than the first chromatogram correlation reference value, such as 0.9 and 0.7, respectively);
for each chromatogram classification set, when the number of chromatograms to be analyzed in the chromatogram classification set is less than or equal to a preset chromatogram number reference value, marking a fault state determination result of a chromatograph to be diagnosed corresponding to a first chromatogram to be analyzed included in the chromatogram classification set as a first fault state determination result, and marking a fault state determination result of a chromatograph to be diagnosed corresponding to other chromatograms to be analyzed except for the first chromatogram to be analyzed included in the chromatogram classification set as a second fault state determination result, or when the number of chromatograms to be analyzed included in the chromatogram classification set is greater than the chromatogram number reference value, marking a fault state determination result of a chromatograph to be diagnosed corresponding to each chromatogram to be analyzed included in the chromatogram classification set as a second fault state determination result, wherein the first fault state determination result is used for reflecting that the corresponding chromatograph to be diagnosed has a fault, and the second fault state determination result is used for reflecting that the chromatograph to be diagnosed does not have a fault.
With reference to fig. 3, an embodiment of the present invention further provides a chromatograph fault diagnosis analysis apparatus, which is applicable to the chromatograph fault diagnosis analysis system. Wherein, the chromatograph fault diagnosis analysis device can comprise the following software functional modules:
the chromatogram acquisition module is used for acquiring a plurality of chromatograms to be analyzed corresponding to the plurality of chromatographs to be diagnosed, and the plurality of chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed;
the chromatogram comparison module is used for carrying out chromatogram comparison analysis processing on each two to-be-analyzed chromatograms in the plurality of to-be-analyzed chromatograms to output the chromatogram correlation degree between the two to-be-analyzed chromatograms, and the chromatogram correlation degree is used for reflecting the correlation degree between chromatographic signals;
and the fault state determination module is used for determining fault states of the chromatographs to be diagnosed according to the chromatogram correlation degree between every two chromatograms to be analyzed in the chromatograms to be analyzed so as to output a fault state determination result corresponding to each chromatograph to be diagnosed, wherein the fault state determination result is used for reflecting whether the corresponding chromatograph to be diagnosed has faults or not.
In summary, according to the method and the system for diagnosing and analyzing the chromatograph fault provided by the present invention, a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed are obtained. And for each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, performing chromatogram comparison analysis processing on the two chromatograms to be analyzed so as to output the chromatogram correlation degree between the two chromatograms to be analyzed. And according to the chromatogram correlation degree between every two chromatograms to be analyzed in the chromatograms to be analyzed, fault state determination processing is carried out on the chromatographs to be diagnosed, so that a fault state determination result corresponding to each chromatograph to be diagnosed is output. Based on this, because the plurality of chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed, the chromatograms to be analyzed should have a higher degree of correlation when the chromatographs to be diagnosed are not in fault, and therefore, the fault state determination result corresponding to each chromatograph to be diagnosed can be reliably determined based on the degree of correlation of the chromatograms between every two chromatograms to be analyzed, so that the reliability of fault diagnosis and analysis of the chromatographs is improved to a certain extent, and the defects of the prior art are overcome.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims (8)

1. A chromatograph fault diagnosis analysis method is characterized by comprising the following steps:
acquiring a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed, wherein the chromatograms to be analyzed are obtained by detecting the same target detection object through the plurality of chromatographs to be diagnosed;
for each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, performing chromatogram comparison analysis processing on the two chromatograms to be analyzed to output a chromatogram correlation degree between the two chromatograms to be analyzed, wherein the chromatogram correlation degree is used for reflecting the correlation degree between chromatographic signals;
according to the chromatogram correlation degree between every two chromatograms to be analyzed in the chromatograms to be analyzed, performing fault state determination processing on the chromatographs to be diagnosed so as to output a fault state determination result corresponding to each chromatograph to be diagnosed, wherein the fault state determination result is used for reflecting whether the corresponding chromatograph to be diagnosed has a fault or not;
wherein, for each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed, performing chromatogram contrast analysis processing on the two chromatograms to be analyzed to output the chromatogram correlation degree between the two chromatograms to be analyzed, the method comprises the following steps:
carrying out any marking treatment on the two chromatograms to be analyzed so as to respectively mark and form a comparison chromatogram to be analyzed and a reference chromatogram to be analyzed;
respectively carrying out spectrum segmentation operation on the chromatogram to be analyzed and the reference chromatogram to be analyzed to form a chromatogram fragment sequence to be analyzed and a chromatogram fragment sequence to be analyzed corresponding to the chromatogram to be analyzed and the reference chromatogram fragment sequence to be analyzed and corresponding to the chromatogram to be analyzed;
for each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed, determining the graph fragment importance of the chromatogram fragment to be analyzed, and analyzing the similarity between the chromatogram fragment to be analyzed and the reference chromatogram fragment to be analyzed with the maximum similarity in the chromatogram fragment sequence to be analyzed, so as to mark the similarity as the representative similarity corresponding to the chromatogram fragment to be analyzed;
for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining the graph segment importance of the reference to-be-analyzed chromatogram segment, and analyzing the similarity between the reference to-be-analyzed chromatogram segment and the comparison to-be-analyzed chromatogram segment with the maximum similarity in the comparison to-be-analyzed chromatogram segment sequence to mark the representative similarity corresponding to the reference to-be-analyzed chromatogram segment;
analyzing and outputting the chromatogram correlation degree between the chromatogram to be analyzed and the reference chromatogram to be analyzed based on the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and the corresponding representative similarity, and combining the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and the corresponding representative similarity;
if there is no same chromatogram fragment to be analyzed between chromatogram fragment sequence portions to be analyzed corresponding to two chromatogram fragment sequences to be analyzed respectively, assigning a chromatogram fragment importance corresponding to a chromatogram fragment to be analyzed in the two chromatogram fragment sequences to be analyzed as a difference value between a preset importance default and a chromatogram fragment importance of the chromatogram fragment to be analyzed, wherein the two chromatogram fragment sequence portions to be analyzed are formed based on chromatogram fragments to be analyzed, which are respectively screened out from the two chromatogram fragment sequences to be analyzed, of which corresponding chromatogram fragment importance is not less than an importance reference value, the chromatogram fragment to be analyzed is a chromatogram fragment to be analyzed, which is matched with the chromatogram fragment to be analyzed with the largest similarity in the chromatogram fragment sequences to be analyzed except the chromatogram fragment sequence to be analyzed to which the chromatogram fragment to be analyzed belongs, the two chromatogram fragments to be analyzed are matched and represented, and the similarity between the two chromatogram fragments to be analyzed is greater than or equal to the preset similarity reference value;
the step of analyzing and outputting the chromatogram correlation between the chromatogram to be analyzed and the reference chromatogram to be analyzed based on the graph fragment importance and the corresponding representative similarity corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed and combining the graph fragment importance and the corresponding representative similarity corresponding to each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed, includes:
performing sum value calculation on a map fragment importance degree corresponding to each chromatogram fragment to be analyzed and a corresponding multiplication result value representing similarity included in two chromatogram fragment sequences to be analyzed so as to output a corresponding fusion calculation result value, wherein the two chromatogram fragment sequences to be analyzed include the comparison chromatogram fragment sequence to be analyzed and the reference chromatogram fragment sequence to be analyzed, and each chromatogram fragment to be analyzed belongs to the comparison chromatogram fragment to be analyzed or the reference chromatogram fragment to be analyzed;
performing sum value calculation on the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed included in the two chromatogram fragment sequences to be analyzed to output a corresponding importance degree calculation result value;
and analyzing and outputting the chromatogram correlation between the chromatogram to be analyzed and the reference chromatogram to be analyzed based on the fusion calculation result value and the importance calculation result value.
2. The method for diagnosing and analyzing a malfunction of a chromatograph according to claim 1, wherein the step of acquiring a plurality of chromatograms to be analyzed corresponding to a plurality of chromatographs to be diagnosed includes:
determining a plurality of chromatographs to be diagnosed, wherein the number of the chromatographs to be diagnosed is greater than or equal to the number of preset target instruments;
for each chromatograph to be diagnosed in the plurality of chromatographs to be diagnosed, controlling the chromatograph to be diagnosed to perform detection processing on a target detection object so that the chromatograph to be diagnosed generates a corresponding chromatogram to be analyzed for the target detection object, and extracting the chromatogram to be analyzed from the chromatograph to be diagnosed after the chromatograph to be diagnosed generates the chromatogram to be analyzed.
3. The chromatograph fault diagnosis analysis method according to claim 1, wherein the step of performing a sum calculation on the graph fragment importance degree corresponding to each chromatogram fragment to be analyzed included in the two chromatogram fragment sequences to be analyzed and the corresponding multiplied result value representing the similarity to output a corresponding fused calculation result value comprises:
if the parts of the chromatogram fragment sequences to be analyzed corresponding to the chromatogram fragment sequences to be analyzed respectively do not have the same chromatogram fragment to be analyzed, matching confirmation processing is carried out on each chromatogram fragment to be analyzed in the two chromatogram fragment sequences to be analyzed and the chromatogram fragment to be analyzed with the highest similarity in the chromatogram fragment sequences to be analyzed except the chromatogram fragment sequence to be analyzed to which the chromatogram fragment to be analyzed belongs, and if the matching confirmation processing result reflects that the two corresponding chromatogram fragments to be analyzed are matched, the similarity between the two chromatogram fragments to be analyzed is larger than or equal to a preset similarity reference value;
for the analyzed chromatogram segment to be analyzed which is matched with the chromatogram segment to be analyzed with the maximum similarity in other chromatogram segment sequences to be analyzed, performing difference calculation on a preset importance default and the map segment importance corresponding to the chromatogram segment to be analyzed so as to output the updated map segment importance corresponding to the chromatogram segment to be analyzed;
marking the graph fragment importance degree corresponding to the chromatogram fragment to be analyzed as the updated graph fragment importance degree corresponding to the chromatogram fragment to be analyzed aiming at the analyzed chromatogram fragment to be unmatched with the chromatogram fragment to be analyzed with the maximum similarity in other chromatogram fragment sequences to be analyzed;
and performing sum value calculation on a multiplication result value between the importance degree of the updated map segment corresponding to each chromatogram segment to be analyzed in the two chromatogram segment sequences to be analyzed and the corresponding representative similarity so as to output a corresponding fusion calculation result value.
4. The method as claimed in claim 1, wherein the step of determining, for each chromatogram fragment to be analyzed in the sequence of chromatogram fragments to be analyzed, the graph fragment importance of the chromatogram fragment to be analyzed, and analyzing the similarity between the chromatogram fragment to be analyzed and the chromatogram fragment to be analyzed with the highest similarity in the sequence of chromatogram fragments to be analyzed, so as to mark the representative similarity corresponding to the chromatogram fragment to be analyzed, comprises:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, determining the graph segment importance of the chromatogram segment to be analyzed; and for each chromatogram fragment to be analyzed in the chromatogram fragment sequence to be analyzed, determining whether a chromatogram fragment to be analyzed has a reference chromatogram fragment to be analyzed having a similar relationship with the chromatogram fragment to be analyzed according to a preset chromatogram fragment similarity relationship set, and under the condition that the chromatogram fragment to be analyzed has the reference chromatogram fragment to be analyzed having a similar relationship with the chromatogram fragment to be analyzed, marking the similarity corresponding to the similar relationship in the chromatogram fragment similarity relationship set as the representative similarity corresponding to the chromatogram fragment to be analyzed;
the step of determining the graph fragment importance of the reference to-be-analyzed chromatogram fragment for each reference to-be-analyzed chromatogram fragment in the reference to-be-analyzed chromatogram fragment sequence, analyzing the similarity between the reference to-be-analyzed chromatogram fragment and the comparison to-be-analyzed chromatogram fragment with the maximum similarity in the comparison to-be-analyzed chromatogram fragment sequence, and marking the similarity as the representative similarity corresponding to the reference to-be-analyzed chromatogram fragment comprises the following steps:
determining the graph fragment importance degree of each reference chromatogram fragment to be analyzed in the reference chromatogram fragment to be analyzed sequence; and for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining whether a comparison to-be-analyzed chromatogram segment having a similar relationship with the reference to-be-analyzed chromatogram segment exists in the comparison to-be-analyzed chromatogram segment sequence according to a preset chromatogram segment similar relationship set, and under the condition that the comparison to-be-analyzed chromatogram segment having a similar relationship with the reference to-be-analyzed chromatogram segment exists in the comparison to-be-analyzed chromatogram segment sequence, marking the similarity corresponding to the similar relationship in the chromatogram segment similar relationship set as the representative similarity corresponding to the reference to-be-analyzed chromatogram segment.
5. The chromatograph fault diagnosis and analysis method according to claim 1, wherein the step of determining, for each chromatogram fragment to be analyzed in the sequence of the chromatogram fragments to be analyzed, a graph fragment importance degree of the chromatogram fragment to be analyzed, and analyzing a similarity between the chromatogram fragment to be analyzed and a reference chromatogram fragment to be analyzed having a highest similarity in the sequence of the chromatogram fragments to be analyzed to mark a representative similarity corresponding to the chromatogram fragment to be analyzed comprises:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, determining the graph segment importance degree of the chromatogram segment to be analyzed, mining a neural network by utilizing chromatogram features formed by network optimization, performing feature mining processing on the chromatogram segment to be analyzed to output the feature distribution of the chromatogram segment to be analyzed corresponding to the chromatogram segment to be analyzed, performing feature mining processing on each chromatogram segment to be analyzed included in the chromatogram segment sequence to be analyzed to output the feature distribution of the chromatogram segment to be analyzed corresponding to each chromatogram segment to be analyzed, calculating the feature distribution similarity between the feature distribution of the chromatogram segment to be analyzed to be compared and the feature distribution of each chromatogram segment to be analyzed, and marking the feature distribution similarity with the maximum value as the representative similarity corresponding to the chromatogram segment to be analyzed;
the step of determining the graph fragment importance of each reference chromatogram fragment to be analyzed in the reference chromatogram fragment sequence to be analyzed, analyzing the similarity between the reference chromatogram fragment to be analyzed and the comparison chromatogram fragment to be analyzed with the highest similarity in the comparison chromatogram fragment sequence to be analyzed, and marking the similarity as the representative similarity corresponding to the reference chromatogram fragment to be analyzed comprises the following steps:
for each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence, determining the graph segment importance of the reference to-be-analyzed chromatogram segment, mining a neural network by utilizing chromatogram features formed by network optimization, performing feature mining processing on the reference to-be-analyzed chromatogram segment to output the feature distribution of the reference to-be-analyzed chromatogram segment corresponding to the reference to-be-analyzed chromatogram segment, performing feature mining processing on each comparison to-be-analyzed chromatogram segment included in the comparison to-be-analyzed chromatogram segment sequence to output the feature distribution of the comparison to-be-analyzed chromatogram segment corresponding to each comparison to-be-analyzed chromatogram segment, calculating the feature distribution similarity between the feature distribution of the reference to-be-analyzed chromatogram segment and the feature distribution of each comparison to-be-analyzed chromatogram segment, and marking the feature distribution similarity with the maximum value as the representative similarity corresponding to the reference to-analyzed chromatogram segment.
6. The chromatograph fault diagnosis and analysis method according to claim 5, wherein the step of determining, for each chromatogram segment to be analyzed in the sequence of the chromatogram segments to be analyzed, the graph segment importance degree of the chromatogram segment to be analyzed, comprises:
for each chromatogram segment to be analyzed in the chromatogram segment sequence to be analyzed, respectively calculating the similarity between the chromatogram segment to be analyzed and each target chromatogram segment in a preset target chromatogram segment set, and analyzing the graph segment importance of the chromatogram segment to be analyzed based on the similarity and the segment importance preset for each target chromatogram segment;
the step of determining the map segment importance of each reference to-be-analyzed chromatogram segment in the reference to-be-analyzed chromatogram segment sequence comprises the following steps:
for each reference chromatogram segment to be analyzed in the reference chromatogram segment sequence to be analyzed, respectively calculating the similarity between the reference chromatogram segment to be analyzed and each target chromatogram segment in a preset target chromatogram segment set, and analyzing the graph segment importance of the reference chromatogram segment to be analyzed based on the similarity and the segment importance preset for each target chromatogram segment.
7. The chromatograph fault diagnosis and analysis method according to any one of claims 1 to 6, wherein the step of performing fault state determination processing on the plurality of chromatographs to be diagnosed according to the chromatogram correlation between each two chromatograms to be analyzed in the plurality of chromatograms to be analyzed to output a fault state determination result corresponding to each chromatograph to be diagnosed comprises:
for each chromatogram to be analyzed in the plurality of chromatograms to be analyzed, performing mean value calculation on the chromatogram correlation degree between the chromatogram to be analyzed and each other chromatogram to be analyzed except the chromatogram to be analyzed so as to output a representative chromatogram correlation degree corresponding to the chromatogram to be analyzed;
for each chromatogram to be analyzed in the plurality of chromatograms to be analyzed, comparing the correlation degree of the representative chromatogram corresponding to the chromatogram to be analyzed with a preset first chromatogram correlation degree reference value, and labeling the chromatogram to be analyzed as the first chromatogram to be analyzed when the correlation degree of the representative chromatogram corresponding to the chromatogram to be analyzed is smaller than the first chromatogram correlation degree reference value;
classifying the plurality of chromatograms to be analyzed according to the chromatogram correlation degree between every two chromatograms to be analyzed in the plurality of chromatograms to be analyzed to form at least one chromatogram classification set corresponding to the plurality of chromatograms to be analyzed, wherein each chromatogram classification set comprises at least one chromatogram to be analyzed, and for each chromatogram classification set comprising the plurality of chromatograms to be analyzed, the chromatogram correlation degree between any two chromatograms to be analyzed in the chromatogram classification set is greater than or equal to a second preset chromatogram correlation degree reference value;
for each chromatogram classification set, when the number of chromatograms to be analyzed in the chromatogram classification set is less than or equal to a preset chromatogram number reference value, labeling a fault state determination result of a chromatograph to be diagnosed corresponding to a first chromatogram to be analyzed included in the chromatogram classification set as a first fault state determination result, and labeling a fault state determination result of a chromatograph to be diagnosed corresponding to other chromatograms to be analyzed except for the first chromatogram to be analyzed included in the chromatogram classification set as a second fault state determination result, or, when the number of chromatograms to be analyzed in the chromatogram classification set is greater than the chromatogram number reference value, labeling a fault state determination result of a chromatograph to be diagnosed corresponding to each chromatogram classification set as a second fault state determination result, wherein the first fault state determination result is used for reflecting that the corresponding chromatograph to be diagnosed has a fault, and the second fault state determination result is used for reflecting that the chromatograph to be diagnosed corresponding to has no fault.
8. A chromatograph malfunction diagnosis analysis system characterized by comprising a processor and a memory for storing a computer program, the processor being configured to execute the computer program to implement the chromatograph malfunction diagnosis analysis method according to any one of claims 1 to 7.
CN202211187579.8A 2022-09-28 2022-09-28 Chromatograph fault diagnosis analysis method and system Active CN115267035B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202211187579.8A CN115267035B (en) 2022-09-28 2022-09-28 Chromatograph fault diagnosis analysis method and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202211187579.8A CN115267035B (en) 2022-09-28 2022-09-28 Chromatograph fault diagnosis analysis method and system

Publications (2)

Publication Number Publication Date
CN115267035A CN115267035A (en) 2022-11-01
CN115267035B true CN115267035B (en) 2022-12-09

Family

ID=83756945

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202211187579.8A Active CN115267035B (en) 2022-09-28 2022-09-28 Chromatograph fault diagnosis analysis method and system

Country Status (1)

Country Link
CN (1) CN115267035B (en)

Families Citing this family (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116106465B (en) * 2023-04-11 2023-06-16 华谱科仪(北京)科技有限公司 Chromatograph fault diagnosis method and device based on parameter analysis
CN118606869A (en) * 2024-08-02 2024-09-06 杭州携测信息技术股份有限公司 Chromatograph fault diagnosis analysis method and system based on data processing

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5782711A (en) * 1980-11-11 1982-05-24 Mitsubishi Heavy Ind Ltd Fault detecting method of detector
CN104007212A (en) * 2014-06-23 2014-08-27 华中科技大学 Method for extracting and analyzing chromatography characteristic peak wave bands based on local similarity matching
JP2017181138A (en) * 2016-03-29 2017-10-05 一般財団法人電力中央研究所 Photovoltaic power generation facility abnormality diagnostic method, abnormality diagnostic device, and abnormality diagnostic program
CN114166988A (en) * 2022-02-09 2022-03-11 华谱科仪(北京)科技有限公司 Chromatograph cluster fault detection method and device
CN114372063A (en) * 2022-01-21 2022-04-19 华谱科仪(北京)科技有限公司 Fault detection method based on chromatograph and electronic equipment
WO2022162999A1 (en) * 2021-01-26 2022-08-04 株式会社島津製作所 Chromatography device

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JPS5782711A (en) * 1980-11-11 1982-05-24 Mitsubishi Heavy Ind Ltd Fault detecting method of detector
CN104007212A (en) * 2014-06-23 2014-08-27 华中科技大学 Method for extracting and analyzing chromatography characteristic peak wave bands based on local similarity matching
JP2017181138A (en) * 2016-03-29 2017-10-05 一般財団法人電力中央研究所 Photovoltaic power generation facility abnormality diagnostic method, abnormality diagnostic device, and abnormality diagnostic program
WO2022162999A1 (en) * 2021-01-26 2022-08-04 株式会社島津製作所 Chromatography device
CN114372063A (en) * 2022-01-21 2022-04-19 华谱科仪(北京)科技有限公司 Fault detection method based on chromatograph and electronic equipment
CN114166988A (en) * 2022-02-09 2022-03-11 华谱科仪(北京)科技有限公司 Chromatograph cluster fault detection method and device

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于层次分析的变压器故障诊断决策支持系统;王俊良 等;《武汉大学学报(工学版)》;20081228(第06期);全文 *
气相色谱仪的维护与故障排除;周建钟 等;《实验室科学》;20121228(第06期);全文 *

Also Published As

Publication number Publication date
CN115267035A (en) 2022-11-01

Similar Documents

Publication Publication Date Title
CN115267035B (en) Chromatograph fault diagnosis analysis method and system
CN110554958B (en) Graph database testing method, system, device and storage medium
CN107798047B (en) Repeated work order detection method, device, server and medium
CN110352389B (en) Information processing apparatus and information processing method
CN112416643A (en) Unsupervised anomaly detection method and unsupervised anomaly detection device
CN115620211B (en) Performance data processing method and system of flame-retardant low-smoke halogen-free sheath
CN109521725A (en) The method, apparatus and equipment and machine readable media of detection abnormal data
CN112416662A (en) Multi-time series data anomaly detection method and device
CN116126947B (en) Big data analysis method and system applied to enterprise management system
CN113409284A (en) Circuit board fault detection method, device, equipment and storage medium
CN111860447A (en) Method for accurately identifying telemetry time sequence data mode of random phase shift satellite
CN116821777A (en) Novel basic mapping data integration method and system
CN115601564B (en) Colloid contour detection method and system based on image recognition
CN110991473A (en) Feature selection method and device for image sample, computer equipment and storage medium
CN115047262A (en) General equipment abnormal state identification method based on power quality data
CN115631448B (en) Audio and video quality inspection processing method and system
CN116994609B (en) Data analysis method and system applied to intelligent production line
CN111340349A (en) Product reliability evaluation method and device, computer equipment and storage medium
Ling et al. Usage Space Sampling for Fringe Customer Identification.
CN114580982B (en) Method, device and equipment for evaluating data quality of industrial equipment
US20220252647A1 (en) Method of generating metadata from acquired signals for search, filtering, and machine learning inputs
CN115761311A (en) Performance detection data analysis method and system of PVC calcium zinc stabilizer
Hochbrückner et al. Application of a cluster-algorithm for partial discharge analysis at DC voltage under practical conditions
CN117411821A (en) Data transmission method and system based on communication path matching
CN117315423A (en) User early warning method and system based on intelligent building

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant