CN116577451B - Large chromatograph data management system and method - Google Patents
Large chromatograph data management system and method Download PDFInfo
- Publication number
- CN116577451B CN116577451B CN202310631702.9A CN202310631702A CN116577451B CN 116577451 B CN116577451 B CN 116577451B CN 202310631702 A CN202310631702 A CN 202310631702A CN 116577451 B CN116577451 B CN 116577451B
- Authority
- CN
- China
- Prior art keywords
- sensing data
- processor
- data
- preset condition
- chromatograph
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 73
- 238000013523 data management Methods 0.000 title claims abstract description 23
- 230000002159 abnormal effect Effects 0.000 claims abstract description 23
- 238000012545 processing Methods 0.000 claims description 56
- 239000011159 matrix material Substances 0.000 claims description 44
- 238000003860 storage Methods 0.000 claims description 44
- 230000005856 abnormality Effects 0.000 claims description 30
- 230000001360 synchronised effect Effects 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 13
- 230000007246 mechanism Effects 0.000 claims description 10
- 230000002776 aggregation Effects 0.000 claims description 3
- 238000004220 aggregation Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 21
- 230000006870 function Effects 0.000 description 13
- 239000000243 solution Substances 0.000 description 12
- 238000004458 analytical method Methods 0.000 description 11
- 238000012544 monitoring process Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 238000004590 computer program Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 4
- 238000003491 array Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013500 data storage Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000003672 processing method Methods 0.000 description 3
- 230000003068 static effect Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000012512 characterization method Methods 0.000 description 2
- 238000004587 chromatography analysis Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000007781 pre-processing Methods 0.000 description 2
- 239000000941 radioactive substance Substances 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 206010000117 Abnormal behaviour Diseases 0.000 description 1
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 description 1
- 230000005526 G1 to G0 transition Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 238000000840 electrochemical analysis Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000002347 injection Methods 0.000 description 1
- 239000007924 injection Substances 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000002285 radioactive effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
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
- G01N30/88—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N35/00—Automatic analysis not limited to methods or materials provided for in any single one of groups G01N1/00 - G01N33/00; Handling materials therefor
- G01N35/00584—Control arrangements for automatic analysers
-
- 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
- G01N30/88—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86
- G01N2030/8804—Integrated analysis systems specially adapted therefor, not covered by a single one of the groups G01N30/04 - G01N30/86 automated systems
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/02—Total factory control, e.g. smart factories, flexible manufacturing systems [FMS] or integrated manufacturing systems [IMS]
Abstract
The application relates to the technical field of chromatographs, in particular to a chromatograph management system, and specifically relates to a large chromatograph data management system and method; the device comprises a plurality of chromatograph which are independently deployed, wherein a plurality of sensors for corresponding data acquisition are arranged in the chromatograph, the device further comprises a first processor, a second processor, a sensor and a CPU, the first processor and the second processor can acquire sensing data of a plurality of sensors, and the CPU acquires a plurality of sensing data of the first processor and the second processor. According to the technical scheme provided by the embodiment of the application, aiming at the terminal system for carrying out data management on a plurality of chromatographs, a processor is added in the existing data management system, the abnormal recognition is carried out on the sensing data from the plurality of sensors obtained by the sensors through the processor, and the acquisition strategy of the corresponding CPU on the sensing data is determined based on the result of the abnormal recognition.
Description
Technical Field
The application relates to the technical field of chromatographs, in particular to a chromatograph management system, and particularly relates to a large chromatograph data management system and method.
Background
Instrument analysis has developed to date to form modern instrument analysis with electrochemical analysis, optical analysis, chromatographic analysis and spectroscopic analysis as support. The chromatographic analysis is an analysis method realized according to the difference of partition coefficients of different substances in a stationary phase and a mobile phase, and is particularly suitable for the rapid and efficient analysis of an organic mixture.
Along with the rapid development of computer technology, the computer technology can promote the analysis automation of the instrument, and the computer is used as a component part of the analysis instrument, so that the automation of data acquisition, processing and display of the analysis instrument is realized, the parameters are automatically regulated according to the preset parameters, and the whole analysis process is completed without manual intervention. The computer also promotes the disappearance of many traditional analytical instrument components, such as recorders, oscilloscopes, integrators, etc., making the instrument more flexible and precise. The computer also realizes automation of traditional manual operation which is difficult to replace, such as a chromatographic automatic sample injection device, and can automatically complete all analysis processes of tens of samples according to respective analysis conditions.
However, the management of the existing chromatograph automation is mainly based on the management of a single chromatograph through a single network condition or a mode of establishing management at a chromatograph station of an area, but the management requirement on chromatograph data related to a large-scale chromatograph deployment scene is high, and no better scheme is realized at present. How to realize the synchronous management of the chromatograph deployed on a large scale belongs to the technical problem to be solved at present.
Disclosure of Invention
In order to solve the technical problems, the application provides the large-scale chromatograph data management system and the large-scale chromatograph data management method, which can synchronously manage a plurality of chromatographs under the condition of large-scale arrangement, identify the actual characterization situation of data by preprocessing the data while acquiring chromatograph data in real time, realize dynamic data acquisition by data characterization, and reduce errors of data processing caused by non-real-time processing on the basis of reducing the data acquisition cost and improving the data processing efficiency.
In order to achieve the above purpose, the technical scheme adopted by the embodiment of the application is as follows:
in a first aspect, a large-scale chromatograph data management system is provided, including a plurality of chromatograph deployed independently, in which a plurality of sensors for corresponding data acquisition are arranged, and further including a first processor, a second processor, and a CPU, the first processor and the second processor being capable of acquiring sensing data of a plurality of the sensors, the CPU acquiring a plurality of sensing data of the first processor and the second processor; the plurality of sensors comprise any one of a temperature sensor, a humidity sensor and a gas flow sensor, the first processor is an asynchronous processor, the second processor is a synchronous processor, and the first processor comprises a receiving and transmitting module, a data processing module and an instruction issuing module; the transceiver module is used for receiving a plurality of sensing data of a plurality of sensors; the data processing module is used for comparing the plurality of sensing data with a first preset condition and a second preset condition to obtain a comparison result; the instruction issuing module issues a starting command to the second processor based on the comparison result; the data processing module comprises a first processing unit and a second processing unit, wherein the first processing unit is used for comparing any one of a plurality of sensing data with a first preset condition to obtain a first comparison result; and the second processing unit compares any one of the plurality of sensing data with a second preset condition based on the first comparison result to obtain a second comparison result.
Further, the processor further includes a classifier, configured to identify a plurality of data type tags of the sensing data, and send the sensing data of the corresponding data type tags to the corresponding first processor and the second processor based on a preset matching mechanism.
Further, the first processor is configured with a first storage space and a second storage space, the CPU collects a plurality of sensing data in the first storage space based on a first collection strategy, and the CPU collects a plurality of sensing data in the second storage space based on a second collection strategy; the first storage space stores a plurality of sensing data which meet the first preset condition and the second preset condition and have the same time sequence, and the second storage space stores a plurality of sensing data to be identified which do not meet the second preset condition but do not have abnormality.
In a second aspect, a method for managing data of a large-scale chromatograph is provided, which is applied to the data management system described in any one of the above, and the method includes: when the first processor detects that any one of the plurality of sensing data does not meet a first preset condition, a first control instruction is sent to a second processor so as to trigger the first processor to stop running, the plurality of sensing data under the same time sequence are transmitted to the second processor, and the second processor is started; when the first processor detects that any one of the plurality of sensing data meets a first preset condition but does not meet a second preset condition, carrying out abnormal recognition on the plurality of sensing data under the same time sequence, judging whether the plurality of sensing data to be recognized are abnormal or not, sending a first control instruction to the second processor to trigger the first processor to stop running, transmitting the plurality of sensing data to be recognized under the same time sequence to the second processor, and starting the second processor; judging whether a plurality of sensing data to be identified have abnormality or not, comprising: and taking the time sequence of the plurality of sensing data to be identified as a node, acquiring a plurality of reference sensing data in a past preset time period, and identifying the sensing data to be identified and the plurality of reference sensing data when any one of the plurality of reference sensing data does not meet a first preset condition, so as to judge whether the plurality of sensing data to be identified has abnormality.
Further, before collecting the sensing data, the method further comprises: and identifying a plurality of type labels of the sensing data, and collecting the sensing data of the corresponding data type labels based on a preset matching mechanism.
Further, the method further comprises: and storing the plurality of sensing data which do not meet the first preset condition and the plurality of sensing data which meet the first preset condition but do not meet the second preset condition and have no abnormality into different storage spaces based on a preset storage mechanism.
Further, the method further comprises: and acquiring a plurality of sensing data which meet the first preset condition and the second preset condition and a plurality of sensing data which meet the first preset condition but do not meet the second preset condition and have no abnormality at different acquisition frequencies based on a preset CPU data acquisition strategy.
Further, a plurality of reference sensing data in a past preset time period are acquired by taking a time sequence of a plurality of sensing data to be identified as nodes, when any one of the plurality of reference sensing data does not meet a first preset condition, a first control instruction is sent to the second processor so as to trigger the first processor to stop running, the sensing data to be identified and the plurality of reference sensing data are transmitted to the second processor, and the second processor is started.
Further, the identifying the sensing data to be identified and the plurality of reference sensing data, and determining whether the plurality of sensing data to be identified has an abnormality includes: extracting a plurality of to-be-identified sensing data and a plurality of characteristics corresponding to a plurality of reference sensing data, and carrying out aggregation processing on the characteristics to obtain a characteristic matrix; reconstructing the initial feature matrix to obtain a target feature matrix; and acquiring a reconstruction error of each sensing data in the target feature matrix, comparing the reconstruction error with a threshold value corresponding to each sensing data, and judging whether the target feature matrix is abnormal or not.
Further, the target feature matrix is obtained by an encoder provided with a convolution neural network, and the target feature matrix is obtained by a decoder provided with a deconvolution neural network; the number of convolution layers of the encoder is the same as the number of deconvolution layers of the decoder.
According to the technical scheme provided by the embodiment of the application, aiming at the terminal system for carrying out data management on a plurality of chromatographs, a processor is added in the existing data management system, the abnormal recognition is carried out on the sensing data from the plurality of sensors obtained by the sensors through the processor, and the acquisition strategy of the corresponding CPU on the sensing data is determined based on the result of the abnormal recognition. And the recognition of the abnormality comprises at least the recognition of the dominant abnormality and the recognition of the invisible abnormality, and different acquisition strategies are set for the dominant abnormality and the invisible abnormality recognition modes and the corresponding CPU acquisition modes. The method and the configuration of the components solve the problem of calculation pressure for processing the acquired data in the prior art, and can realize the configuration of data processing optimization.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
The methods, systems, and/or programs in the accompanying drawings will be described further in terms of exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein the exemplary numbers represent like mechanisms throughout the various views of the drawings.
Fig. 1 is a schematic diagram of a chromatograph data management system according to an embodiment of the present application.
Fig. 2 is a flowchart of an overall method provided by an embodiment of the present application.
FIG. 3 is a flowchart of a particular process of a method of updating sensor data, according to some embodiments of the application.
Detailed Description
In order to better understand the above technical solutions, the following detailed description of the technical solutions of the present application is made by using the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and the embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limiting the technical solutions of the present application, and the technical features of the embodiments and the embodiments of the present application may be combined with each other without conflict.
In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant teachings. It will be apparent, however, to one skilled in the art that the application can be practiced without these details. In other instances, well known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.
The present application uses a flowchart to illustrate the execution of a system according to an embodiment of the present application. It should be clearly understood that the execution of the flowcharts may be performed out of order. Rather, these implementations may be performed in reverse order or concurrently. Additionally, at least one other execution may be added to the flowchart. One or more of the executions may be deleted from the flowchart.
Before describing embodiments of the present application in further detail, the terms and terminology involved in the embodiments of the present application will be described, and the terms and terminology involved in the embodiments of the present application will be used in the following explanation.
(1) In response to a condition or state that is used to represent the condition or state upon which the performed operation depends, the performed operation or operations may be in real-time or with a set delay when the condition or state upon which it depends is satisfied; without being specifically described, there is no limitation in the execution sequence of the plurality of operations performed.
(2) Based on the conditions or states that are used to represent the operations that are being performed, one or more of the operations that are being performed may be in real-time or with a set delay when the conditions or states that are being relied upon are satisfied; without being specifically described, there is no limitation in the execution sequence of the plurality of operations performed.
(3) Self-encoder, self-encoder (AE) is a type of artificial neural networks (Artificial Neural Networks, ans) used in semi-supervised learning and non-supervised learning, whose function is to characterize the input information by taking it as a learning target (representation learning).
The technical scheme provided by the embodiment of the application has the main application scene of collecting, processing and managing equipment data in the running process of the chromatograph. In the present scenario, the running state of the chromatograph in its key components when working is performed, data acquisition is performed by the sensors configured in the specific chromatograph, and recording of the chromatograph working state is achieved based on the acquired data. With the increase of the degree of intelligence, the collection of data in the running process of the chromatograph is not just a recording function, but monitoring and judging whether the running of the chromatograph is safe or not based on the running state of the real-time running data (especially for the chromatograph under special conditions, such as a radioactive chromatograph, which needs to determine the concentration of the radioactive substance in the chromatograph and whether the radioactive substance is missing or not during running), so that the real-time acquisition and the real-time judgment cannot be realized. In particular, there is no existing solution for unified process data collection, processing and judgment for mass-deployed chromatograph systems, and as the number of chromatographs in the system increases, the capacity requirements for data processing increase. In addition, in the process of processing the data acquired by the sensor, the processing process mainly calls the acquired corresponding sensing data through the data acquisition command of the CPU. In the current processing scenario, the sensor is usually passive, and the CPU is required to read repeatedly to obtain the sensor data, which occupies the CPU time, and the power consumption is high, especially for the chromatograph system deployed on a large scale. Against the background of the technology, the large-scale chromatograph data management system and method provided by the embodiment can realize corresponding storage of the data collected by the sensors arranged in the chromatograph deployed on a large scale, and retrieve the stored monitoring data based on the collection strategy of the CPU, and the entity executing mechanism for the method is a processor configured between the CPU and the sensors, wherein the processor is configured with a corresponding sensor data updating method, so that the technical effects are realized.
The terminal device comprises the sensor, the processor and the CPU, and a computer program stored in the processor and capable of running on the processor, wherein the processor executes a sensor data updating method, processes the monitoring data acquired by the sensor and uploads the corresponding monitoring data to the corresponding CPU based on the acquisition command of the CPU.
In other embodiments, the specific sensing data may also be directly transmitted to the display device to directly display the monitoring data.
In this embodiment, the sensor, the processor, the CPU, and each element of the communication unit are directly or indirectly electrically connected to each other, so as to implement data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines.
The processor in this embodiment may be an integrated circuit chip with signal processing capabilities. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also Digital Signal Processors (DSPs)), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Referring to fig. 1, in this embodiment, a large-scale chromatograph data management system is provided, where the system includes a plurality of chromatograph deployed independently, where a plurality of sensors for data collection are disposed in the chromatograph, and the system further includes a first processor, a second processor, a sensor, and a CPU, where the first processor, the second processor, the sensor, the CPU, and the plurality of chromatograph are electrically connected to perform data transmission, that is, the first processor, the second processor, the sensor, the CPU, and the chromatograph are not disposed on one physical unit, and the sensor is disposed in a physical space of the corresponding chromatograph, and is used to collect key indicators in the corresponding chromatograph.
Specifically, the first processor and the second processor can collect sensing data of a plurality of sensors, and the CPU collects a plurality of sensing data of the first processor and the second processor. The plurality of sensors include any one of a temperature sensor, a humidity sensor and a gas flow sensor, and in other embodiments, different sensors can be configured according to different chromatographs, wherein the configuration of the sensors is mainly based on the acquisition requirement of key data indexes in the chromatographs.
In this embodiment, the first processor is an asynchronous processor, and the second processor is a synchronous processor, where the first processor includes a transceiver module, a data processing module, and an instruction issuing module.
Specifically, the transceiver module is configured to receive a plurality of sensing data of a plurality of sensors. The data processing module is used for comparing the plurality of sensing data with a first preset condition and a second preset condition to obtain a comparison result. And the instruction issuing module issues a starting command to the second processor based on the comparison result.
In this embodiment, the data processing module includes a first processing unit and a second processing unit, where the first processing unit is configured to compare any one of the plurality of sensing data with a first preset condition to obtain a first comparison result; and the second processing unit compares any one of the plurality of sensing data with a second preset condition based on the first comparison result to obtain a second comparison result.
Specifically, the processor in this embodiment further includes a classifier, configured to identify a plurality of data type tags of the sensing data, and send the sensing data of the corresponding data type tag to the corresponding first processor and the second processor based on a preset matching mechanism.
In order to achieve the storage of different data of the result, in the embodiment, the first processor is configured with a first storage space and a second storage space, the CPU collects a plurality of sensing data in the first storage space based on a first collection strategy, and the CPU collects a plurality of sensing data in the second storage space based on a second collection strategy; the first storage space stores a plurality of sensing data which meet the first preset condition and the second preset condition and have the same time sequence, and the second storage space stores a plurality of sensing data to be identified which do not meet the second preset condition but do not have abnormality.
For the large-scale chromatograph data management system provided in this embodiment, a data management method is also provided, which is used to explain the working processes of the first processor, the second processor and the CPU. When the sensor obtains sensing data, the sensing data are firstly sent to a processor, a corresponding data processing method is arranged for the processor, whether the sensing data are abnormal or not is judged based on the collected sensing data of the sensor, and the data with the abnormality and the data without the abnormality are pushed through ports corresponding to a CPU according to the set rule. The rules aiming at the setting comprise synchronous data pushing rules and asynchronous data pushing rules, wherein the synchronous data pushing rules are used for realizing synchronous collection of the CPU on a plurality of sensing data, and the asynchronous data pushing rules are used for realizing asynchronous collection of the CPU on a plurality of sensing data. It can be understood that the data object for asynchronous collection is the sensing data which does not affect the data processing requirement of the CPU, and the data object for synchronous collection is the sensing data which affects the data processing requirement of the CPU. Through the arrangement, the problem of high acquisition cost caused by real-time data acquisition can be reduced on the basis that the accuracy of data processing of the CPU is not affected.
The main logic for identifying whether the plurality of sensing data will affect the CPU is to identify whether the plurality of sensing data has an anomaly, and since the processing priority of the normal data is lower than that of the anomaly data, the anomaly data can represent a specific anomaly, the embodiment performs subsequent data update processing mainly by identifying the anomaly data of the plurality of sensing data. For this logic, the general processing method in the prior art mainly determines whether the individual real-time sensing data is in the error value range of the normal data based on the statistical method, and determines the abnormality of the data based on the determination result. However, the method has a large error in a plurality of sensing data acquired by a plurality of sensors, and firstly, the acquisition of the error value is based on manual setting, so that the problem of inaccurate identification is easily generated. Moreover, based on the condition of big data, the data have a large correlation, and the behaviors represented by the whole data are possibly abnormal under the condition that all single-point data are in an error range. Therefore, in order to improve the CPU processing efficiency and reduce the technical problems caused by inaccurate judgment, the present embodiment provides the method, which includes the following steps:
And S210, the processor identifies a plurality of type labels of the sensing data, and acquires the sensing data of the type labels based on a preset matching mechanism.
In this embodiment, the configuration of the sensors may be collected for different collection purposes, and generally, the sensors are divided into two types, where the first type is a sensor for collecting corresponding values, for example, a temperature sensor is used for collecting temperature data; another type of sensor, such as an image sensor, for acquiring corresponding types of information is used to acquire corresponding image information.
Based on such an application scenario, a determination needs to be made regarding the type of data before the identification of a plurality of sensing data is performed. The setting of the process is mainly based on processing logic of data, the sensing data acquired by the multiple sensors not only comprises specific parameter data but also comprises non-parameter data such as image data, and the data which is complex such as image data or can be processed directly through a CPU or a GPU and the displayed data do not need to be processed directly through abnormality identification. The setting of the data type label can be preset based on the corresponding sensor, for example, the sensor for collecting the data is the image data, the registration of the corresponding number is performed before the system establishment is performed, and the type of the corresponding sensing data can be realized through the acquisition of the sensor number in the collected multiple sensing data by the processor. The acquisition logic of the CPU is synchronous acquisition aiming at the image data, namely, when the processor acquires the image data, the CPU directly acquires the image data acquired by the processor.
The corresponding acquisition strategies are different for two different types of data, namely synchronous acquisition of the CPU is realized by a synchronous processor, namely a second processor, for the data of the non-numerical type of the image, and asynchronous acquisition of the CPU is realized by an asynchronous processor, namely a first processor, for the data of the numerical type.
And S220, detecting whether any one of the plurality of sensing data meets a first preset condition by the first processor, and selecting a corresponding first processor or second processor based on a detection result.
In this embodiment, if the asynchronous collection of the CPU is implemented by the first processor for a plurality of sensing data of a numerical value type, although the cost problem of data collection of the CPU is solved, the problem of subsequent control errors and the like that are caused by data abnormality and are not processed in time is caused because the data is not processed. Therefore, in order to reduce the problem caused by abnormal behavior in the plurality of sensing data but not even if the sensing data is not timely processed, a first abnormality judgment scheme is provided in this embodiment, that is, by monitoring whether any one of the plurality of sensors satisfies a first preset condition, where the first preset condition is a standard variation threshold of the plurality of sensing data, where the standard variation threshold is an acceptable maximum fluctuation threshold of the corresponding sensing data, that is, by comparing the maximum fluctuation threshold with real-time fluctuation values of the plurality of sensing data, it is determined whether the first preset condition is satisfied, and when the first preset condition is not satisfied, that is, the fluctuation value of the sensing data is no longer within the maximum fluctuation threshold range, that is, the sensing data is abnormal data, and processing is performed on the abnormal data by a second processor, that is, a synchronization processor, and synchronous acquisition is performed by a CPU. In this embodiment, the determination of the maximum fluctuation threshold may be set based on experience, and may also be obtained through a neural network in a convergence state, and the determination of the threshold for the neural network may be performed by using a semi-supervised neural network structure, where training for the neural network may be performed by marking random data in a training set, and the convergence of the final neural network may be achieved by a semi-supervised manner. The acquisition of the real-time fluctuation data for the sensing data can be determined by the difference value between the real-time sensing data and the standard sensing data, wherein the acquisition of the real-time fluctuation data for the sensing data can be determined by a preset mode in advance.
The process for the above is specifically as follows: when any one of the plurality of sensing data does not meet a first preset condition, namely, the data fluctuation range of any one of the plurality of sensing data is larger than a maximum fluctuation threshold value of a preset value, a first control instruction is sent to a second processor to trigger the first processor to stop running, the plurality of sensing data under the same time sequence are transmitted to the second processor, and the second processor is started.
And in this embodiment, correlation among a plurality of sensing data should be considered, so that the CPU needs to collect not only the corresponding point data but also a plurality of sensing data under the same time sequence for the collection of the abnormal data.
In this embodiment, the first processor is an asynchronous processor, that is, a processor for which a plurality of sensor data acquired asynchronously with respect to the CPU are to be stored.
And S230, the first processor detects whether any one of the plurality of sensing data meets a second preset condition.
When the maximum fluctuation threshold value for any one of the plurality of the sensing data detected by the first processor is in the first preset condition in step S220, in order to more accurately obtain the abnormal expression in the plurality of the sensing data, the identification of the abnormality for the changed data in the plurality of the sensing data is realized by setting the second preset condition, and whether the abnormality exists in the plurality of the sensing data is determined. Specifically, the second preset condition is a second threshold value, that is, when the change of the plurality of the sensing data based on the preset basic sensing data is smaller than the first threshold value but larger than the second threshold value, the plurality of the sensing data is subjected to the recognition of the abnormality for the case and the control based on the first processor and the second processor in the case. The method comprises the following steps: and when the sensing data to be identified are abnormal, a first control instruction is sent to the second processor so as to trigger the first processor to stop running, and the sensing data to be identified under the same time sequence are transmitted to the second processor and are started.
In this embodiment, if the data is processed only at the same time sequence, the recognition result is inaccurate because the data amount is smaller. The sensing data for identification is sensing data for a certain period of time for this case. The method comprises the following steps: and taking the time sequence of the plurality of sensing data to be identified as a node, acquiring a plurality of reference sensing data in a backward preset time period, and sending a first control instruction to the second processor when judging that any one of the plurality of reference sensing data meets a first preset condition so as to trigger the first processor to stop running, and transmitting the sensing data to be identified and the plurality of reference sensing data to the second processor, wherein the second processor is started.
Referring to fig. 3, the above processing method specifically includes the following steps:
s231, extracting a plurality of to-be-identified sensing data and a plurality of features corresponding to the reference sensing data, and carrying out aggregation processing on the features to obtain a feature matrix.
In the present embodiment, first, time series data m= (m) with a sequence length T and a sensing data dimension n for a plurality of sensing data to be identified and a plurality of reference sensing data are constructed 1 ，m 2 ，...，m 3 ) T ∈R n×T . For the extraction of features from this time series data, in order to represent the correlation between the multiple features in the ω to t time period, the sequence from ω to t is noted as L ωt, assuming that the total number of features is nN, it is apparent that L ωt is N vectors of length ω. Constructing an N x N feature matrix M by using cosine similarity of two variables in Lωt sequence t Specifically, the matrix for construction is:
wherein, aim atFor the variables->Variable->Is related to (a)Sex, characteristic matrix M t Not only can the similarity between two variables be captured, but also the robustness is better, because the influence of the fluctuation of a specific time sequence on the feature matrix is smaller.
For the constructed initial time series data feature matrix, a convolutional encoder is used to encode the spatial pattern of the system feature matrix. Specifically, mt is connected as a tensor X on different scales t，0 ∈R n×n×s It is then output to several convolutional layers. Wherein the method comprises the steps ofRepresenting the feature matrix of the L layer, the output of the L layer is expressed as follows:
X t，l ∈f(W l *X t，l-1 +b l )；
* Representing a convolution operation, f (·) representing an activation function, W l ∈R kl×kl×dl-1×sl Representing a size k l ×k l ×s l-1 D of (2) l Convolution kernels, b l ∈R sl Is a bias term, X t,l ∈R nl×nl×sl Representing the output feature matrix of the first layer. In this embodiment, X represents an input matrix, where the input matrix is obtained by rolling and processing a plurality of convolution layers, where l is l convolution layers, the representation of the convolution kernel and the representation of the offset term performed by b are all commonly used parameter representations, R represents a real set, and is also a common parameter representation, and k represents a parameter.
In the present embodiment, the above feature extraction process is based on the self-encoder, in which the convolutional neural network is provided in the self-encoder in the present embodiment, wherein the number of convolutional layers in the convolutional neural network is 4.
S232, reconstructing the initial feature matrix to obtain a target feature matrix.
The decoding is performed on the initial feature matrix obtained in step S231 to obtain a reconstructed feature matrix, and the decoding process in this embodiment is implemented based on a decoder, where a deconvolution neural network is disposed in the decoder, that is, the decoder in this embodiment is a deconvolution decoder, and specifically, the following formula is used for a convolution decoder:
where x represents the deconvolution operation,is a concatenation operation, f (·) activates a function, +.>Andis the convolution kernel and offset parameters of the first deconvolution layer. Specifically, the first layer in reverse orderInput to the next deconvolution neural network. To increase the fitting capacity of the network, the feature matrix will be output hereinThe decoding process is stacked by being connected to the output of the previous layer of ALSTM. The series representation is input to the next deconvolution layer. Final output- >A representation of the reconstructed feature matrix. In the deconvolution neural network in the present embodiment, 4 deconvolution layers are also configured.
S233, acquiring a reconstruction error of each sensing data in the target feature matrix, comparing the reconstruction error with a threshold value corresponding to each sensing data, and judging whether the target feature matrix is abnormal or not.
The processing for this procedure mainly defines the objective function as the reconstruction error of the feature matrix, namely:
wherein, aim atThe objective function is:
in this embodiment, t represents time, c represents a variable, and the matrix based on t and c relative to x can be expressed asThe real number matrix expressed as an nn multiplication is the corresponding estimation matrix, i.e. the corresponding norm is obtained by the difference between the two matrices. For example, when t=1, c=1, the corresponding value is obtained, and when t=2, c=1, the corresponding value is obtained, that is, different matrices and corresponding norms are obtained with time t as the change, and the sum is performed according to the summation logic based on the number of t changes. Similarly, for t=1, c=1; the corresponding norms are solved for t=1 and c=2, and summed based on summing logic according to the corresponding variation. The general expression in the solution process for the norm for F in the present embodiment is not described in the present embodiment, but in the present embodiment, the solution process for the norm is described:
Wherein A, U each represent a matrix.
The logical meaning of this function in this embodiment is: and carrying out data preprocessing on the data set, namely constructing a feature matrix, after obtaining a corresponding feature matrix, reconstructing the feature matrix, taking the reconstructed matrix as an estimation matrix, subtracting corresponding elements of the reconstructed matrix, squaring, comparing the elements with a set threshold value for each element, and calculating the number exceeding the threshold value.
In this embodiment, a small batch random gradient descent method and Adam optimizer are used to minimize the objective function.
It should be noted that, if the result obtained by the above processing is non-abnormal, but when the plurality of reference sensing data in the backward preset time period has sensing data that does not satisfy the first preset condition, the sensing data that does not satisfy the first preset condition still needs to be processed according to the processing manner of step S230.
Step S240, collecting a plurality of sensing data meeting a first preset condition and a plurality of sensing data meeting a second preset condition and having no abnormality at different collection frequencies based on a preset CPU data collection strategy.
For steps S220-S230, mainly for abnormality recognition of a plurality of the sensing data, the first processor and the second processor are controlled based on the recognized abnormality data. And the processing controlled by the first processor and the second processor mainly realizes the acquisition of different data by the CPU.
In this embodiment, the first processor is an asynchronous processor, that is, the CPU performs acquisition on the basis of an asynchronous acquisition policy for acquiring the plurality of sensing data in the first processor, that is, the plurality of sensing data in the first processor is acquired at a certain acquisition frequency, and the second processor is a synchronous processor, that is, the CPU performs acquisition on the basis of a synchronous acquisition policy for acquiring the plurality of sensing data in the second processor. The plurality of acquired data in the first processor is configured with different acquisition strategies based on data of different abnormal conditions, and the non-abnormal data in the first processor comprises a plurality of sensing data meeting a first preset condition and a plurality of sensing data meeting the first preset condition, not meeting a second preset condition but not having an abnormality. Since the anomaly identification method in step S230 of the present embodiment is not a final complete anomaly identification method in order to reduce the processing cost, the anomaly identification method needs to perform the second identification after the acquisition of the CPU, so that the plurality of sensing data satisfying the first preset condition, which does not satisfy the second preset condition but does not have anomalies, are more sensitive to the second condition than the plurality of sensing data satisfying the first preset condition, and the relative acquisition frequency in the CPU data acquisition strategy is higher than the plurality of sensing data satisfying the first preset condition. Therefore, for the above case, it is necessary to configure different acquisition frequencies for acquisition.
Therefore, at least two data storage spaces, namely a first storage space and a second storage space, are arranged in the first processor, wherein the first storage space is used for storing a plurality of sensing data meeting a first preset condition, and the plurality of sensing data under the same time sequence are combined and stored. The second storage space is used for storing a plurality of sensing data which do not meet the first preset condition, meet the second preset condition and have no abnormality, and combining and storing the plurality of sensing data under the same time sequence. In the present embodiment, the merging and storing of a plurality of sensing data based on the same time series belongs to the prior art, and the implementation of this process will not be described in detail.
The setting of the storage capacities for the first storage space and the second storage space may be based on a redundant manner of the allowed data amount in the data acquisition policy. By configuring different data acquisition frequencies, the method realizes one-time acquisition of a plurality of sensing data stored in the first storage space and the second storage space, reduces the cost of the CPU for data acquisition, and ensures the timeliness of key data processing.
In addition, in other embodiments, in order to improve the security of data storage for the data in the first storage space and the second storage space, a data encryption method may be specifically provided, and the data encryption method may be implemented by using a mapping encryption manner, because the mapping encryption is one of the existing encryption manners, which is not described in this embodiment.
The following describes each component of the processor in detail:
wherein in this embodiment the processor is a specific integrated circuit (application specific integrated circuit, ASIC), or one or more integrated circuits configured to implement embodiments of the present application, such as: one or more microprocessors (digital signalprocessor, DSPs), or one or more field programmable gate arrays (fieldprogrammable gate array, FPGAs).
Alternatively, the processor may perform various functions, such as performing the method shown in fig. 2 described above, by running or executing a software program stored in memory, and invoking data stored in memory.
In a particular implementation, the processor may include one or more microprocessors, as one embodiment.
The memory is configured to store a software program for executing the scheme of the present application, and the processor is used to control the execution of the software program, and the specific implementation manner may refer to the above method embodiment, which is not described herein again.
Alternatively, the memory may be read-only memory (ROM) or other type of static storage device that can store static information and instructions, random access memory (random access memory, RAM) or other type of dynamic storage device that can store information and instructions, but may also be, without limitation, electrically erasable programmable read-only memory (electrically erasable programmable read-only memory, EEPROM), compact disc read-only memory (compact disc read-only memory) or other optical disk storage, optical disk storage (including compact disc, laser disc, optical disc, digital versatile disc, blu-ray disc, etc.), magnetic disk storage media or other magnetic storage devices, or any other medium that can be used to carry or store desired program code in the form of instructions or data structures and that can be accessed by a computer. The memory may be integrated with the processor or may exist separately and be coupled to the processing unit through an interface circuit of the processor, which is not particularly limited by the embodiment of the present application.
It should be noted that the structure of the processor shown in this embodiment is not limited to the apparatus, and an actual apparatus may include more or less components than those shown in the drawings, or may combine some components, or may be different in arrangement of components.
In addition, the technical effects of the processor may refer to the technical effects of the method described in the foregoing method embodiments, which are not described herein.
It should be appreciated that the processor in embodiments of the application may be other general purpose processors, digital signal processors (digital signal processor, DSP), application specific integrated circuits (application specific integrated circuit, ASIC), off-the-shelf programmable gate arrays (field programmable gate array, FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
It should also be appreciated that the memory in embodiments of the present application may be either volatile memory or nonvolatile memory, or may include both volatile and nonvolatile memory. The nonvolatile memory may be a read-only memory (ROM), a Programmable ROM (PROM), an Erasable PROM (EPROM), an electrically Erasable EPROM (EEPROM), or a flash memory. The volatile memory may be random access memory (random access memory, RAM) which acts as an external cache. By way of example but not limitation, many forms of random access memory (random access memory, RAM) are available, such as Static RAM (SRAM), dynamic Random Access Memory (DRAM), synchronous Dynamic Random Access Memory (SDRAM), double data rate synchronous dynamic random access memory (DDR SDRAM), enhanced Synchronous Dynamic Random Access Memory (ESDRAM), synchronous Link DRAM (SLDRAM), and direct memory bus RAM (DR RAM).
The above embodiments may be implemented in whole or in part by software, hardware (e.g., circuitry), firmware, or any other combination. When implemented in software, the above-described embodiments may be implemented in whole or in part in the form of a computer program product. The computer program product comprises one or more computer instructions or computer programs. When the computer instructions or computer program are loaded or executed on a computer, the processes or functions described in accordance with embodiments of the present application are produced in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from one website site, computer, server, or data center to another website site, computer, server, or data center by wired (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains one or more sets of available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, magnetic tape), an optical medium (e.g., DVD), or a semiconductor medium. The semiconductor medium may be a solid state disk.
In the present application, "at least one" means one or more, and "a plurality" means two or more. "at least one of" or the like means any combination of these items, including any combination of single item(s) or plural items(s). For example, at least one (one) of a, b, or c may represent: a, b, c, a-b, a-c, b-c, or a-b-c, wherein a, b, c may be single or plural.
It should be understood that, in various embodiments of the present application, the sequence numbers of the foregoing processes do not mean the order of execution, and the order of execution of the processes should be determined by the functions and internal logic thereof, and should not constitute any limitation on the implementation process of the embodiments of the present application.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In the several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods may be implemented in other manners. For example, the apparatus embodiments described above are merely illustrative, e.g., the division of the units is merely a logical function division, and there may be additional divisions when actually implemented, e.g., multiple units or components may be combined or integrated into another system, or some features may be omitted or not performed. Alternatively, the coupling or direct coupling or communication connection shown or discussed with each other may be an indirect coupling or communication connection via some interfaces, devices or units, which may be in electrical, mechanical or other form.
The units described as separate units may or may not be physically separate, and units shown as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.
In addition, each functional unit in the embodiments of the present application may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a read-only memory (ROM), a random access memory (random access memory, RAM), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The foregoing is merely illustrative of the present application, and the present application is not limited thereto, and any person skilled in the art will readily recognize that variations or substitutions are within the scope of the present application. Therefore, the protection scope of the present application shall be subject to the protection scope of the claims.
Claims (6)
1. The large-scale chromatograph data management method is characterized by being applied to a chromatograph data management system, wherein the chromatograph data management system comprises a plurality of chromatograph which are independently deployed, a plurality of sensors for corresponding data acquisition are arranged in the chromatograph, the large-scale chromatograph data management method further comprises a first processor, a second processor, a sensor and a CPU, the first processor and the second processor can acquire sensing data of a plurality of sensors, and the CPU acquires sensing data of the first processor and the second processor; the plurality of sensors comprise any one of a temperature sensor, a humidity sensor and a gas flow sensor, the first processor is an asynchronous processor, the second processor is a synchronous processor, and the first processor comprises a receiving and transmitting module, a data processing module and an instruction issuing module; the transceiver module is used for receiving a plurality of sensing data of a plurality of sensors; the data processing module is used for comparing the plurality of sensing data with a first preset condition and a second preset condition to obtain a comparison result; the instruction issuing module issues a starting command to the second processor based on the comparison result; the data processing module comprises a first processing unit and a second processing unit, wherein the first processing unit is used for comparing any one of a plurality of sensing data with a first preset condition to obtain a first comparison result; the second processing unit compares any one of the plurality of sensing data with a second preset condition based on the first comparison result to obtain a second comparison result;
The method comprises the following steps:
when the first processor detects that any one of the plurality of sensing data does not meet a first preset condition, a first control instruction is sent to a second processor so as to trigger the first processor to stop running, the plurality of sensing data under the same time sequence are transmitted to the second processor, and the second processor is started;
when the first processor detects that any one of the plurality of sensing data meets a first preset condition but does not meet a second preset condition, carrying out abnormal recognition on the plurality of sensing data under the same time sequence, judging whether the plurality of sensing data to be recognized are abnormal or not, sending a first control instruction to the second processor to trigger the first processor to stop running, transmitting the plurality of sensing data to be recognized under the same time sequence to the second processor, and starting the second processor;
judging whether a plurality of sensing data to be identified have abnormality or not, comprising: taking the time sequence of the plurality of sensing data to be identified as a node, acquiring a plurality of reference sensing data in a past preset time period, and identifying the sensing data to be identified and the plurality of reference sensing data when any one of the plurality of reference sensing data does not meet a first preset condition, so as to judge whether the plurality of sensing data to be identified is abnormal;
The method further comprises the steps of:
acquiring a plurality of sensing data meeting a first preset condition and a second preset condition and a plurality of sensing data meeting the first preset condition but not meeting the second preset condition and having no abnormality at different acquisition frequencies based on a preset CPU data acquisition strategy;
taking the time sequence of the plurality of sensing data to be identified as a node, acquiring a plurality of reference sensing data in a past preset time period, and when any one of the plurality of reference sensing data does not meet a first preset condition, sending a first control instruction to the second processor to trigger the first processor to stop running, transmitting the sensing data to be identified and the plurality of reference sensing data to the second processor, and starting the second processor;
the sensing data to be identified and a plurality of reference sensing data are identified, and whether the sensing data to be identified are abnormal or not is judged, including:
extracting a plurality of to-be-identified sensing data and a plurality of characteristics corresponding to a plurality of reference sensing data, and carrying out aggregation processing on the characteristics to obtain a characteristic matrix;
reconstructing the initial feature matrix to obtain a target feature matrix;
And acquiring a reconstruction error of each sensing data in the target feature matrix, comparing the reconstruction error with a threshold value corresponding to each sensing data, and judging whether the target feature matrix is abnormal or not.
2. The method of claim 1, further comprising, prior to collecting the sensor data: and identifying a plurality of type labels of the sensing data, and collecting the sensing data of the corresponding data type labels based on a preset matching mechanism.
3. The method of large scale chromatograph data management of claim 1, further comprising: and storing the plurality of sensing data which do not meet the first preset condition and the plurality of sensing data which meet the first preset condition but do not meet the second preset condition and have no abnormality into different storage spaces based on a preset storage mechanism.
4. The large-scale chromatograph data management method according to claim 1, characterized in that the characteristic matrix is obtained by an encoder provided with a convolutional neural network, and the target characteristic matrix is obtained by a decoder provided with a deconvolution neural network; the number of convolution layers of the encoder is the same as the number of deconvolution layers of the decoder.
5. The method of claim 1, wherein the processor further comprises a classifier for identifying a plurality of data type tags of the sensing data, and transmitting the sensing data of the corresponding data type tags to the corresponding first and second processors based on a preset matching mechanism.
6. The method of claim 2, wherein the first processor is configured with a first memory space and a second memory space, the CPU collecting a plurality of sensor data in the first memory space based on a first collection policy, the CPU collecting a plurality of sensor data in the second memory space based on a second collection policy; the first storage space stores a plurality of sensing data which meet the first preset condition and the second preset condition and have the same time sequence, and the second storage space stores a plurality of sensing data to be identified which do not meet the second preset condition but do not have abnormality.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310631702.9A CN116577451B (en) | 2023-05-31 | 2023-05-31 | Large chromatograph data management system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310631702.9A CN116577451B (en) | 2023-05-31 | 2023-05-31 | Large chromatograph data management system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116577451A CN116577451A (en) | 2023-08-11 |
| CN116577451B true CN116577451B (en) | 2023-10-17 |
Family
ID=87545174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310631702.9A Active CN116577451B (en) | 2023-05-31 | 2023-05-31 | Large chromatograph data management system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116577451B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101650567A (en) * | 2009-07-29 | 2010-02-17 | 厦门集芯科技有限公司 | Zero-emission pig-raising wireless measuring and controlling system |
| CN104598007A (en) * | 2014-12-29 | 2015-05-06 | 联想(北京)有限公司 | Data processing method and electronic device |
| CN113780370A (en) * | 2021-08-23 | 2021-12-10 | 咪咕文化科技有限公司 | Visual question answering method, device, equipment and storage medium |
| WO2022105005A1 (en) * | 2020-11-19 | 2022-05-27 | 深圳市鹰硕教育服务有限公司 | Smart classroom information exchange method, apparatus, and electronic device |
| WO2022105003A1 (en) * | 2020-11-23 | 2022-05-27 | 深圳市鹰硕教育服务有限公司 | Medical information processing method and apparatus, and electronic device |
| CN115238828A (en) * | 2022-09-16 | 2022-10-25 | 华谱科仪(北京)科技有限公司 | Chromatograph fault monitoring method and device |
| CN115549027A (en) * | 2022-11-24 | 2022-12-30 | 中国电力科学研究院有限公司 | Pressing plate state online monitoring system and method |
| CN115965354A (en) * | 2022-11-21 | 2023-04-14 | 潍柴动力股份有限公司 | Operation and maintenance system and method for fuel cell energy station |
-
2023
- 2023-05-31 CN CN202310631702.9A patent/CN116577451B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101650567A (en) * | 2009-07-29 | 2010-02-17 | 厦门集芯科技有限公司 | Zero-emission pig-raising wireless measuring and controlling system |
| CN104598007A (en) * | 2014-12-29 | 2015-05-06 | 联想(北京)有限公司 | Data processing method and electronic device |
| WO2022105005A1 (en) * | 2020-11-19 | 2022-05-27 | 深圳市鹰硕教育服务有限公司 | Smart classroom information exchange method, apparatus, and electronic device |
| WO2022105003A1 (en) * | 2020-11-23 | 2022-05-27 | 深圳市鹰硕教育服务有限公司 | Medical information processing method and apparatus, and electronic device |
| CN113780370A (en) * | 2021-08-23 | 2021-12-10 | 咪咕文化科技有限公司 | Visual question answering method, device, equipment and storage medium |
| CN115238828A (en) * | 2022-09-16 | 2022-10-25 | 华谱科仪(北京)科技有限公司 | Chromatograph fault monitoring method and device |
| CN115965354A (en) * | 2022-11-21 | 2023-04-14 | 潍柴动力股份有限公司 | Operation and maintenance system and method for fuel cell energy station |
| CN115549027A (en) * | 2022-11-24 | 2022-12-30 | 中国电力科学研究院有限公司 | Pressing plate state online monitoring system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116577451A (en) | 2023-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Paparrizos et al. | Volume under the surface: a new accuracy evaluation measure for time-series anomaly detection | |
| Nikolaou et al. | Detection of early warning signals in paleoclimate data using a genetic time series segmentation algorithm | |
| US20230388202A1 (en) | Methods and systems for inferred information propagation for aircraft prognostics | |
| Jozdani et al. | A regression modelling approach for optimizing segmentation scale parameters to extract buildings of different sizes | |
| CN115801463B (en) | Industrial Internet platform intrusion detection method and device and electronic equipment | |
| CN113110961B (en) | Equipment abnormality detection method and device, computer equipment and readable storage medium | |
| CN117388893B (en) | Multi-device positioning system based on GPS | |
| CN114610572A (en) | Service abnormity detection method, device, computer equipment and storage medium | |
| Jogarah et al. | Hybrid machine learning algorithms for fault detection in android smartphones | |
| Li et al. | Nonlinear dynamic process monitoring using deep dynamic principal component analysis | |
| CN116577451B (en) | Large chromatograph data management system and method | |
| CN108701147A (en) | Method and system for automatic identification agroclimate area | |
| Wang et al. | Adaptive change detection for long-term machinery monitoring using incremental sliding-window | |
| CN115932144B (en) | Chromatograph performance detection method, chromatograph performance detection device, chromatograph performance detection equipment and computer medium | |
| CN116740586A (en) | Hail identification method, hail identification device, electronic equipment and computer readable storage medium | |
| CN110874601B (en) | Method for identifying running state of equipment, state identification model training method and device | |
| Dang et al. | Trend-adaptive multi-scale PCA for data fault detection in IoT networks | |
| Yu et al. | Data anomaly detection and data fusion based on incremental principal component analysis in fog computing | |
| CN115757365A (en) | Multi-dimensional time sequence data anomaly detection method, model training method and device | |
| KR102343139B1 (en) | Method and appartus for anomaly detectioin | |
| CN114401205A (en) | Non-annotation multi-source network flow data drift detection method and device | |
| Aparna et al. | Comparison of feature reduction techniques for change detection in remote sensing | |
| WO2018177293A1 (en) | Sample-based multidimensional data cloning | |
| Papst et al. | Exploring co-dependency of iot data quality and model robustness in precision cattle farming | |
| CN115631799B (en) | Sample phenotype prediction method and device, electronic equipment and storage medium |
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 |