CN116594364A - Optimization method and system based on prefabricated vegetable production control system - Google Patents
Optimization method and system based on prefabricated vegetable production control system Download PDFInfo
- Publication number
- CN116594364A CN116594364A CN202310696098.8A CN202310696098A CN116594364A CN 116594364 A CN116594364 A CN 116594364A CN 202310696098 A CN202310696098 A CN 202310696098A CN 116594364 A CN116594364 A CN 116594364A
- Authority
- CN
- China
- Prior art keywords
- abnormal
- production control
- label
- cluster core
- target
- 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.)
- Pending
Links
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 242
- 238000000034 method Methods 0.000 title claims abstract description 50
- 238000005457 optimization Methods 0.000 title claims abstract description 27
- 235000013311 vegetables Nutrition 0.000 title claims abstract description 22
- 230000002159 abnormal effect Effects 0.000 claims abstract description 736
- 239000013598 vector Substances 0.000 claims abstract description 171
- 238000012512 characterization method Methods 0.000 claims abstract description 44
- 230000004927 fusion Effects 0.000 claims description 20
- 238000012549 training Methods 0.000 claims description 16
- 230000005856 abnormality Effects 0.000 claims description 15
- 238000005259 measurement Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 4
- 238000002360 preparation method Methods 0.000 claims 1
- 238000003860 storage Methods 0.000 description 11
- 238000013461 design Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 239000004278 EU approved seasoning Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 239000002778 food additive Substances 0.000 description 1
- 235000013373 food additive Nutrition 0.000 description 1
- 235000011194 food seasoning agent Nutrition 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 244000144977 poultry Species 0.000 description 1
- 239000011265 semifinished product Substances 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B19/00—Programme-control systems
- G05B19/02—Programme-control systems electric
- G05B19/418—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM]
- G05B19/41865—Total factory control, i.e. centrally controlling a plurality of machines, e.g. direct or distributed numerical control [DNC], flexible manufacturing systems [FMS], integrated manufacturing systems [IMS] or computer integrated manufacturing [CIM] characterised by job scheduling, process planning, material flow
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B2219/00—Program-control systems
- G05B2219/30—Nc systems
- G05B2219/32—Operator till task planning
- G05B2219/32252—Scheduling production, machining, job shop
-
- 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]
Landscapes
- Engineering & Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Quality & Reliability (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- General Factory Administration (AREA)
Abstract
The embodiment of the application provides an optimization method and system based on a prefabricated vegetable production control system, which can update an abnormal code vector by using a target abnormal label cluster core to obtain an updated abnormal code vector, and determine target abnormal characterization information corresponding to production control abnormal data based on the updated abnormal code vector, so that the characteristics of abnormal production nodes of richer abnormal labels are obtained, the abnormal code vector is updated by the target abnormal label cluster core to assist in an abnormal root cause positioning process, and the generated target abnormal characterization information is more remarkable. Therefore, the abnormal root cause positioning is performed on the production control abnormal data based on the target abnormal characterization information, the generated abnormal root cause positioning information is higher in accuracy, and the reliability of system optimization is improved.
Description
Technical Field
The application relates to the technical field of system optimization, in particular to an optimization method and system based on a prefabricated vegetable production control system.
Background
The prefabricated vegetable, also called prefabricated conditioning food, is generally a semi-finished product or finished product which is prepared by taking various agricultural, livestock, poultry and aquatic products as raw and auxiliary materials, adding auxiliary materials (containing food additives) such as seasonings and the like, and carrying out preselection, modulation and other processes. In the related art, mass production of the prefabricated dishes can be realized through the prefabricated dish production control system, but real-time abnormality monitoring is needed to be carried out on data in the production control process of the prefabricated dishes so as to determine possible abnormality conditions of the prefabricated dishes and track and position the cause of the abnormality, so that subsequent system optimization is facilitated. However, in the model training and identifying schemes in the prior art, effective and remarkable abnormal characterization information is difficult to obtain in the process of carrying out abnormal root cause tracking and positioning, so that the generated abnormal root cause positioning information is low in precision, and the reliability of subsequent system optimization is affected.
Disclosure of Invention
In view of the above, the present application aims to provide an optimization method and system based on a prefabricated vegetable production control system, which can update an abnormal encoding vector by using a target abnormal tag cluster core to obtain an updated abnormal encoding vector, and determine target abnormal characterization information corresponding to production control abnormal data based on the updated abnormal encoding vector, so as to obtain the characteristics of abnormal production nodes of richer abnormal tags, and update the abnormal encoding vector by using the target abnormal tag cluster core to assist in an abnormal root cause positioning process, so that the generated target abnormal characterization information is more significant. Therefore, the abnormal root cause positioning is performed on the production control abnormal data based on the target abnormal characterization information, the generated abnormal root cause positioning information is higher in accuracy, and the reliability of system optimization is improved.
According to a first aspect of the present application, there is provided an optimization method based on a prefabricated vegetable production control system, applied to a cloud server, the method comprising:
acquiring production control abnormal data of a prefabricated vegetable production control system acquired in a designated production control mode;
encoding the production control abnormal data to obtain an abnormal encoding vector;
Determining a target abnormal label cluster core corresponding to the abnormal coding vector from the abnormal label cluster core data sequence based on the characteristic distance between the abnormal coding vector and the abnormal label cluster core in the abnormal label cluster core data sequence, wherein the abnormal label cluster core data sequence comprises abnormal label cluster cores of different abnormal labels, and the abnormal label cluster cores are significant abnormal vectors corresponding to abnormal production nodes of different abnormal labels;
updating the abnormal coding vector according to the target abnormal label cluster core to obtain an updated abnormal coding vector;
determining target abnormality characterization information corresponding to the production control abnormal data based on the updated abnormality coding vector;
and carrying out abnormal root cause positioning on the production control abnormal data based on the target abnormal characterization information, generating abnormal root cause positioning information, and optimizing the prefabricated vegetable production control system according to the abnormal root cause positioning information.
In a possible implementation manner of the first aspect, the method further includes:
loading the production control abnormal data into an abnormal root cause positioning model, wherein the abnormal root cause positioning model comprises a feature encoder, an abnormal tag cluster core unit, a fusion unit and a prediction unit, and the abnormal tag cluster core unit is composed of abnormal tag cluster cores in the abnormal tag cluster core data sequence;
The encoding the production control abnormal data to obtain an abnormal encoding vector comprises the following steps:
encoding the production control abnormal data according to the characteristic encoder to obtain the abnormal encoding vector;
the determining, based on the feature distance between the anomaly coding vector and the anomaly label cluster core in the anomaly label cluster core data sequence, a target anomaly label cluster core corresponding to the anomaly coding vector from the anomaly label cluster core data sequence includes:
determining the target abnormal label cluster core corresponding to the abnormal coding vector according to the abnormal label cluster core unit; the updating of the abnormal coding vector according to the target abnormal label cluster core to obtain an updated abnormal coding vector comprises the following steps:
fusing the target abnormal label cluster core and the abnormal coding vector according to the fusion unit to generate the updated abnormal coding vector;
the determining the target abnormality characterization information corresponding to the production control abnormal data based on the updated abnormal coding vector includes:
determining the target abnormal characterization information corresponding to the production control abnormal data based on the updated abnormal coding vector according to the fusion unit;
The abnormal root cause positioning of the production control abnormal data based on the target abnormal characterization information, generating abnormal root cause positioning information, includes:
and carrying out abnormal root cause positioning on the production control abnormal data based on the target abnormal characterization information according to the prediction unit, and generating abnormal root cause positioning information.
In a possible implementation manner of the first aspect, the method further includes constructing the abnormal label cluster core unit, and the constructing the abnormal label cluster core unit includes:
in the process of carrying out model weight parameter iterative updating on the abnormal root cause positioning model, encoding the abnormal data of the template production control according to the characteristic encoder, and generating a reference abnormal encoding vector of an abnormal production node marked by an abnormal label attribute, wherein the abnormal label attribute represents an abnormal label of the abnormal production node included in the abnormal data of the template production control;
updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the reference abnormal coding vector of the abnormal production node.
In a possible implementation manner of the first aspect, the updating, based on the reference anomaly encoding vector of the anomaly production node, the anomaly tag cluster core of the anomaly tag to which the anomaly production node belongs in the anomaly tag cluster core unit includes:
If the abnormal label cluster core of the abnormal label which the abnormal production node belongs to is an empty set, taking the reference abnormal coding vector of the abnormal production node as the abnormal label cluster core of the abnormal label which the abnormal production node belongs to;
if the abnormal label cluster core of the abnormal label which the abnormal production node belongs to is not an empty set, calculating the characteristic distance between the reference abnormal coding vector of the abnormal production node and the abnormal label cluster core of the abnormal label which the abnormal production node belongs to;
updating an abnormal label cluster center of an abnormal label to which the abnormal production node belongs in the abnormal label cluster center unit based on the characteristic distance;
the updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the characteristic distance comprises the following steps:
if the characteristic distance is greater than or equal to the threshold distance, adding the reference abnormal coding vector of the abnormal production node into an abnormal label cluster center of an abnormal label to which the abnormal production node belongs;
the updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the characteristic distance comprises the following steps:
If the characteristic distance is larger than or equal to the threshold distance, determining the number relation between the number of the abnormal label cluster centers of the abnormal labels of the abnormal production nodes and the threshold number;
and updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the quantity relation.
In a possible implementation manner of the first aspect, the constructing the abnormal label cluster core unit includes:
constructing a target training cost value based on the difference between the abnormal tag attribute and the obtained reference updated abnormal coding vector;
updating the abnormal label cluster core in the abnormal label cluster core unit based on the target training cost value so as to optimize the abnormal label cluster core unit.
In a possible implementation manner of the first aspect, the determining, from the anomaly tag cluster core data sequence, a target anomaly tag cluster core corresponding to the anomaly encoding vector based on a feature distance between the anomaly encoding vector and an anomaly tag cluster core in the anomaly tag cluster core data sequence, the corresponding different anomaly tag cluster core data sequence in different specified production control modes includes:
Acquiring an abnormal label cluster core data sequence corresponding to the appointed production control mode; and determining the target abnormal label cluster center corresponding to the abnormal coding vector from the abnormal label cluster center data sequence corresponding to the appointed production control mode.
In a possible implementation manner of the first aspect, the determining, based on the updated anomaly encoding vector, target anomaly characterization information corresponding to the production control anomaly data includes:
and fusing the updated abnormal coding vector and the abnormal coding vector to generate the target abnormal characterization information.
In a possible implementation manner of the first aspect, the updating the abnormal encoding vector according to the target abnormal label cluster core to obtain an updated abnormal encoding vector includes:
calculating a characteristic distance measurement array based on the target abnormal label cluster cores and the abnormal coding vectors, wherein array members in the characteristic distance measurement array represent weight values of each target abnormal label cluster core to the abnormal coding vectors;
and carrying out weighted summation on the target abnormal label cluster core and the abnormal coding vector based on the characteristic distance measurement array, and generating the updated abnormal coding vector corresponding to the abnormal coding vector.
In a possible implementation manner of the first aspect, the method further includes:
acquiring template production control abnormal data under a reference production control mode, wherein the template production control abnormal data has an abnormal label attribute of an abnormal production node included in the template production control abnormal data;
loading the template production control abnormal data into an initialization abnormal root cause positioning model, wherein the initialization abnormal root cause positioning model comprises an initial feature encoder, an initial abnormal label cluster core unit, an initial fusion unit and an initial prediction unit, and the template production control abnormal data has an abnormal label attribute of an abnormal production node included in the template production control abnormal data;
coding the template production control abnormal data according to the initial characteristic coder to obtain a reference abnormal coding vector;
determining a target reference abnormal label cluster center corresponding to the reference abnormal code vector from the initial abnormal label cluster center unit based on the characteristic distance between the reference abnormal code vector and the abnormal label cluster center in the abnormal label cluster center data sequence according to the initial abnormal label cluster center unit;
updating the reference abnormal coding vector by utilizing the target reference abnormal label cluster core according to the initial fusion unit to obtain a reference updated abnormal coding vector; determining target reference anomaly characterization information corresponding to the template production control anomaly data based on the reference update anomaly coding vector according to the initial fusion unit;
According to the initial prediction unit, performing abnormal root cause positioning on the production control abnormal data based on the target reference abnormal characterization information, and generating reference abnormal root cause positioning information;
and carrying out model weight parameter iterative updating on the initialized abnormal root cause positioning model according to the abnormal label attribute and the reference abnormal root cause positioning information to generate the abnormal root cause positioning model.
According to a second aspect of the present application, there is provided a cloud server comprising a machine-readable storage medium storing machine-executable instructions and a processor, which when executing the machine-executable instructions, implements the foregoing optimization method based on a prefabricated dish production control system.
According to a third aspect of the present application, there is provided a computer readable storage medium having stored therein computer executable instructions which, when executed, implement the foregoing optimization method based on a pre-dish production control system.
According to any of the above aspects, in the present application, the prototype feature of one anomaly tag may be represented by obtaining in advance the anomaly tag cluster cores of different anomaly tags, where the anomaly tag cluster cores are significant anomaly vectors corresponding to anomaly production nodes of different anomaly tags. When the abnormal root cause positioning is carried out on the production control abnormal data acquired under the appointed production control mode, the production control abnormal data can be encoded to obtain an abnormal encoding vector, and then a target abnormal label cluster center corresponding to the abnormal encoding vector is determined from the abnormal label cluster center data sequence based on the characteristic distance between the abnormal encoding vector and the abnormal label cluster center in the abnormal label cluster center data sequence. The abnormal label cluster core data sequence comprises abnormal label cluster cores of different abnormal labels, the abnormal label cluster cores are significant abnormal vectors corresponding to abnormal production nodes of different abnormal labels, the target abnormal label cluster cores can be utilized to update the abnormal coding vectors to obtain updated abnormal coding vectors, and the target abnormal characterization information corresponding to production control abnormal data is determined based on the updated abnormal coding vectors, so that the characteristics of the abnormal production nodes of the richer abnormal labels are obtained, the target abnormal label cluster cores are utilized to update the abnormal coding vectors to assist in the abnormal root cause positioning process, and the generated target abnormal characterization information can be more significant. Therefore, the abnormal root cause positioning is performed on the production control abnormal data based on the target abnormal characterization information, the generated abnormal root cause positioning information is higher in accuracy, and the reliability of system optimization is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being understood that the following drawings only illustrate some embodiments of the present application and therefore should not be considered as limiting the scope, and other related drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an optimization method based on a prefabricated vegetable production control system according to an embodiment of the present application;
fig. 2 is a schematic component structure diagram of a cloud server for implementing the optimization method based on the prefabricated vegetable production control system according to the embodiment of the present application.
Detailed Description
For the purpose of making the objects, technical solutions and advantages of the embodiments of the present application more clear, the technical solutions of the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it should be understood that the accompanying drawings in the present application are for the purpose of illustration and description only, and are not intended to limit the scope of the present application. In addition, it should be understood that the schematic drawings are not drawn to scale. A flowchart, as used in this disclosure, illustrates operations implemented based on some embodiments of the application. It should be understood that the operations of the flow diagrams may be implemented out of order and that steps without logical context may be performed in reverse order or concurrently. Furthermore, one or more other operations may be added to the flow chart or one or more operations may be destroyed from the flow chart as directed by those skilled in the art in light of the present disclosure.
In addition, the described embodiments are only some, but not all, embodiments of the application. The components of the embodiments of the present application 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 application, as presented in the figures, is not intended to limit the scope of the application, as claimed, but is merely representative of selected embodiments of the application. All other embodiments, which can be made by a person skilled in the art without making any inventive effort, are intended to be within the scope of the present application.
Fig. 1 shows a flow chart of an optimization method based on a prefabricated vegetable production control system according to an embodiment of the present application, and it should be understood that, in other embodiments, the order of part of the steps in the optimization method based on a prefabricated vegetable production control system according to the present application may be shared with each other according to actual needs, or part of the steps may be omitted or maintained. The optimizing method based on the prefabricated vegetable production control system comprises the following steps of:
step S101, acquiring production control abnormal data of the prefabricated vegetable production control system acquired in a designated production control mode.
In an actual implementation process, the embodiment may collect production control abnormal data under various designated production control modes (such as a conventional production control mode, an urgent production control mode, a cooperative production control mode, etc.), and then perform abnormal root cause positioning on the production control abnormal data collected under the designated production control modes, so as to generate more accurate abnormal root cause positioning information. The following embodiments will take a specified production control mode as an example, and production control abnormality data collected under the specified production control mode to perform abnormality root cause localization may be referred to as production control abnormality data.
And step S102, encoding the production control abnormal data to obtain abnormal encoding vectors.
After the production control abnormal data is obtained, the production control abnormal data can be loaded into an abnormal root cause positioning model, so that the abnormal root cause positioning model is used for carrying out abnormal root cause positioning on the production control abnormal data, and abnormal root cause positioning information is generated.
The abnormal root cause positioning model can comprise a feature encoder, an abnormal tag cluster core unit, a fusion unit and a prediction unit, wherein the abnormal tag cluster core unit can be composed of abnormal tag cluster cores in an abnormal tag cluster core data sequence. The method mainly comprises two stages, namely, encoding the production control abnormal data through the abnormal root positioning model, and encoding the production control abnormal data through a feature encoder to obtain an abnormal encoding vector. The second stage is mainly to carry out subsequent positioning according to the extracted abnormal coding vector through an abnormal root cause positioning model, and the second stage mainly needs to use an abnormal label cluster core unit, a fusion unit and a prediction unit.
And step S103, determining a target abnormal label cluster center corresponding to the abnormal coding vector from the abnormal label cluster center data sequence based on the characteristic distance between the abnormal coding vector and the abnormal label cluster center in the abnormal label cluster center data sequence.
In an exemplary design concept, the embodiment may pre-construct an abnormal label cluster core data sequence, where the abnormal label cluster core data sequence includes abnormal label cluster cores of different abnormal labels, and the abnormal label cluster core is a significant abnormal vector corresponding to an abnormal production node of the different abnormal labels. The abnormal tag cluster core data sequence herein may constitute an abnormal tag cluster core unit.
The abnormal label cluster cores in the abnormal label cluster core data sequence can be collected in the model weight parameter iteration updating process of the abnormal root cause positioning model, and in the model weight parameter iteration updating process of the abnormal root cause positioning model, the salient abnormal vector of the abnormal production node of each abnormal label is continuously collected as the abnormal label cluster core of the type, and the abnormal label cluster cores not only participate in the model weight parameter iteration updating process, but also are stored to provide assistance for abnormal root cause positioning.
The embodiment can select the target abnormal label cluster center corresponding to the abnormal coding vector from the abnormal label cluster center data sequence based on the characteristic distance between the abnormal coding vector and the abnormal label cluster center in the abnormal label cluster center data sequence. For example, the feature distance between the anomaly encoding vector and each anomaly tag cluster core in the anomaly tag cluster core data sequence is calculated, and the smaller the feature distance is, the anomaly production node corresponding to the anomaly tag cluster core and the anomaly production node corresponding to the anomaly encoding vector may be the anomaly production node of one anomaly tag, so that the anomaly tag cluster core with the feature distance smaller than the set distance can be used as the target anomaly tag cluster core. Because the abnormal label cluster core data sequence comprises abnormal label cluster cores of different abnormal labels, the abnormal label cluster cores are significant abnormal vectors corresponding to abnormal production nodes of different abnormal labels, and the determined target abnormal label cluster core may be the significant abnormal vector of the abnormal production node corresponding to the abnormal coding vector, the abnormal coding vector can be updated by using the target abnormal label cluster core to obtain updated abnormal coding vectors, and therefore the characteristics of the abnormal production nodes of the richer abnormal labels are obtained.
On the basis of using the abnormal root cause positioning model to perform abnormal root cause positioning, an abnormal label cluster center unit in the abnormal root cause positioning model can be used for determining a target abnormal label cluster center corresponding to the abnormal coding vector.
For the same abnormal production node, different appointed production control modes possibly cause the corresponding saliency abnormal vectors to be different, so that different abnormal label cluster core data sequences corresponding to different appointed production control modes can be constructed. Step S103 may specifically be: and acquiring an abnormal label cluster core data sequence corresponding to the appointed production control mode, and determining a target abnormal label cluster core corresponding to the abnormal coding vector from the abnormal label cluster core data sequence corresponding to the appointed production control mode.
And step S104, updating the abnormal coding vector according to the target abnormal label cluster core to obtain an updated abnormal coding vector.
The abnormal label cluster center (target abnormal label cluster center) of the same abnormal label brings higher-value auxiliary characteristic information, and the fusion unit can be a fusion unit according to an attention mechanism. In this embodiment, a feature distance measurement array may be calculated based on the target abnormal label cluster core and the abnormal code vector, where an array member in the feature distance measurement array characterizes a weight value of each target abnormal label cluster core for the abnormal code vector, and then the target abnormal label cluster core and the abnormal code vector are weighted and summed based on the feature distance measurement array to generate an updated abnormal code vector corresponding to the abnormal code vector.
Step S105, determining target abnormal characterization information corresponding to the production control abnormal data based on the updated abnormal coding vector.
On the basis of using the abnormal root cause positioning model to perform abnormal root cause positioning, the fusion unit can determine the target abnormal characterization information corresponding to the production control abnormal data based on the updated abnormal coding vector.
The method for determining the target abnormal characterization information corresponding to the production control abnormal data based on the updated abnormal coding vector may directly use the updated abnormal coding vector as the target abnormal characterization information, or may fuse the updated abnormal coding vector with the abnormal coding vector to generate the target abnormal characterization information.
And S106, carrying out abnormal root cause positioning on the production control abnormal data based on the target abnormal characterization information, generating abnormal root cause positioning information, and optimizing the production control system of the prepared dish according to the abnormal root cause positioning information.
On the basis of using the abnormal root cause positioning model to perform abnormal root cause positioning, in this embodiment, the production control abnormal data may be subjected to abnormal root cause positioning by the prediction unit based on the target abnormality characterization information, so as to generate abnormal root cause positioning information. The abnormal root cause positioning information may include an abnormal label of an abnormal production node included in the production control abnormal data and a position of the abnormal production node in the production control abnormal data. Therefore, the optimization scheme corresponding to the abnormal label of the abnormal production node can be extracted from the cloud optimization scheme library, and the optimization of the production control source operation is performed in combination with the position of the corresponding abnormal production node in the production control abnormal data.
Based on the steps, the prototype feature of one abnormal label can be represented by acquiring the abnormal label cluster cores of different abnormal labels in advance, wherein the abnormal label cluster cores are significant abnormal vectors corresponding to abnormal production nodes of different abnormal labels. When the abnormal root cause positioning is carried out on the production control abnormal data acquired under the appointed production control mode, the production control abnormal data can be encoded to obtain an abnormal encoding vector, and then a target abnormal label cluster center corresponding to the abnormal encoding vector is determined from the abnormal label cluster center data sequence based on the characteristic distance between the abnormal encoding vector and the abnormal label cluster center in the abnormal label cluster center data sequence. The abnormal label cluster core data sequence comprises abnormal label cluster cores of different abnormal labels, the abnormal label cluster cores are significant abnormal vectors corresponding to abnormal production nodes of different abnormal labels, the target abnormal label cluster cores can be utilized to update the abnormal coding vectors to obtain updated abnormal coding vectors, and the target abnormal characterization information corresponding to production control abnormal data is determined based on the updated abnormal coding vectors, so that the characteristics of the abnormal production nodes of the richer abnormal labels are obtained, the target abnormal label cluster cores are utilized to update the abnormal coding vectors to assist in the abnormal root cause positioning process, and the generated target abnormal characterization information can be more significant. Therefore, the abnormal root cause positioning is performed on the production control abnormal data based on the target abnormal characterization information, the generated abnormal root cause positioning information is higher in accuracy, and the reliability of system optimization is improved.
Next, a training step of the abnormal root cause positioning model of the foregoing embodiment will be described, the method further comprising:
step S201, template production control abnormal data in a reference production control mode is acquired, wherein the template production control abnormal data has an abnormal label attribute of an abnormal production node included in the template production control abnormal data.
Step S202, loading the template production control abnormal data to an initialized abnormal root cause positioning model.
The initialization abnormal root cause positioning model comprises an initial feature encoder, an initial abnormal label cluster core unit, an initial fusion unit and an initial prediction unit, and the template production control abnormal data has abnormal label attributes of abnormal production nodes included in the template production control abnormal data.
And step 203, coding the template production control abnormal data according to the initial characteristic coder to obtain a reference abnormal coding vector.
Step S204, determining a target reference abnormal label cluster center corresponding to the reference abnormal code vector from the initial abnormal label cluster center unit based on the characteristic distance between the reference abnormal code vector and the abnormal label cluster center in the abnormal label cluster center data sequence according to the initial abnormal label cluster center unit.
Step 205, updating the reference abnormal coding vector by using the target reference abnormal label cluster core according to the initial fusion unit to obtain a reference updated abnormal coding vector.
Step S206, determining target reference anomaly characterization information corresponding to the template production control anomaly data based on the reference update anomaly coding vector according to the initial fusion unit.
Step S207, according to the initial prediction unit, performing abnormal root cause positioning on the production control abnormal data based on the target reference abnormal characterization information, and generating reference abnormal root cause positioning information.
And step S208, carrying out model weight parameter iterative updating on the initialized abnormal root cause positioning model according to the abnormal label attribute and the reference abnormal root cause positioning information, and generating the abnormal root cause positioning model.
In the process of training to obtain an abnormal root cause positioning model, an abnormal label cluster core unit can be constructed. The construction of the abnormal label cluster core unit specifically can be that in the process of training to obtain an abnormal root cause positioning model, the abnormal data of the template production control is encoded through a feature encoder, a reference abnormal encoding vector of an abnormal production node marked by an abnormal label attribute is generated, and the abnormal label attribute characterizes an abnormal label of the abnormal production node included in the abnormal data of the template production control; updating the abnormal label cluster center of the abnormal label to which the abnormal production node belongs in the abnormal label cluster center unit based on the reference abnormal coding vector of the abnormal production node.
In the process of training the abnormal root cause positioning model, an abnormal label cluster core unit is introduced and constructed to improve the discriminant representation of damaged abnormal production nodes through the remarkable abnormal vector in the abnormal label cluster core unit, so that the method is beneficial to learning the robust abnormal root cause positioning model.
The method for updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the reference abnormal coding vector of the abnormal production node may be to use the reference abnormal coding vector of the abnormal production node as the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit. Illustratively, the present embodiment may update based on the number of abnormal label cluster cores of the abnormal labels to which the abnormal production nodes belong in the abnormal label cluster core unit. If the abnormal label cluster core of the abnormal label which the abnormal production node belongs to is an empty set, taking the reference abnormal coding vector of the abnormal production node as the abnormal label cluster core of the abnormal label which the abnormal production node belongs to; if the abnormal label cluster center of the abnormal label which the abnormal production node belongs to is not an empty set, calculating the characteristic distance between the reference abnormal coding vector of the abnormal production node and the abnormal label cluster center of the abnormal label which the abnormal production node belongs to, and updating the abnormal label cluster center of the abnormal label which the abnormal production node belongs to in the abnormal label cluster center unit based on the characteristic distance.
In order to avoid excessive number of abnormal label cluster cores in the abnormal label cluster core unit due to addition of the abnormal coding vector, a mode of updating the abnormal label cluster cores of the abnormal labels of the abnormal label cluster core unit, which the abnormal production node belongs to, based on the characteristic distance may be to determine a number relationship between the number of the abnormal label cluster cores of the abnormal labels of the abnormal production node and the threshold number if the characteristic distance is greater than or equal to the threshold distance, and then update the abnormal label cluster cores of the abnormal labels of the abnormal label cluster core unit, which the abnormal production node belongs to, based on the number relationship.
When updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit, in order to obtain an updated abnormal coding vector E with better representation and distinguishability, a target training cost value can be constructed to monitor the updated abnormal coding vector. For example, a target training cost value is constructed based on the difference between the abnormal tag attribute and the obtained reference updated abnormal code vector, and the abnormal tag cluster core in the abnormal tag cluster core unit is updated based on the target training cost value to optimize the abnormal tag cluster core unit.
The target training cost value may be different types of training cost values, such as L2 norm loss, L2 training cost value, L1 training cost value, and the like. Taking the L2 norm as an example, the formula can be as follows:
Ll2＝L2norm(L*Lt–E*Et)
Where L is each anomaly tag attribute, L2norm is the L2 normalization, E is the reference updated anomaly encoding vector, lt, et are coefficients, respectively.
Fig. 2 schematically illustrates a cloud server 100 that may be used to implement various embodiments described in the present disclosure.
For one embodiment, fig. 2 shows a cloud server 100, the cloud server 100 having one or more processors 102, a control module (chipset) 104 coupled to one or more of the processor(s) 102, a memory 106 coupled to the control module 104, a non-volatile memory (NVM)/storage 108 coupled to the control module 104, one or more input/output devices 110 coupled to the control module 104, and a network interface 112 coupled to the control module 106.
The processor 102 may include one or more single-core or multi-core processors, and the processor 102 may include any combination of general-purpose or special-purpose processors (e.g., graphics processors, application processors, baseband processors, etc.). In some exemplary design considerations, the cloud server 100 can be used as a server device such as a gateway in the embodiments of the present application.
In some example design considerations, cloud server 100 may include one or more computer-readable media (e.g., memory 106 or NVM/storage 108) having instructions 114 and one or more processors 102, in conjunction with the one or more computer-readable media, configured to execute instructions 114 to implement modules to perform actions described in this disclosure.
For one embodiment, the control module 104 may include any suitable interface controller to provide any suitable interface to one or more of the processor(s) 102 and/or any suitable device or component in communication with the control module 104.
The control module 104 may include a memory controller module to provide an interface to the memory 106. The memory controller modules may be hardware modules, software modules, and/or firmware modules.
Memory 106 may be used, for example, to load and store data and/or instructions 114 for cloud server 100. For one embodiment, memory 106 may comprise any suitable volatile memory, such as, for example, a suitable DRAM. In some exemplary design considerations, memory 106 may include a double data rate type four synchronous dynamic random access memory (DDR 4 SDRAM).
For one embodiment, control module 104 may include one or more input/output controllers to provide interfaces to NVM/storage 108 and input/output device(s) 110.
For example, NVM/storage 108 may be used to store data and/or instructions 114. NVM/storage 108 may include any suitable nonvolatile memory (e.g., flash memory) and/or may include any suitable nonvolatile storage(s) (e.g., one or more Hard Disk Drives (HDDs), one or more Compact Disc (CD) drives, and/or one or more Digital Versatile Disc (DVD) drives).
NVM/storage 108 may include storage resources that are physically part of the device on which cloud server 100 is installed, or may be accessible by the device without necessarily being part of the device. For example, NVM/storage 108 may be accessed via input/output device(s) 110 according to a network.
Input/output device(s) 110 may provide an interface for cloud server 100 to communicate with any other suitable device, and input/output device 110 may include a communication component, pinyin component, sensor component, and the like. The network interface 112 may provide an interface for the cloud server 100 to communicate in accordance with one or more networks, and the cloud server 100 may communicate wirelessly with one or more components of a wireless network in accordance with any of one or more wireless network standards and/or protocols, such as accessing a wireless network in accordance with a communication standard, such as WwFw, 2G, 3G, 4G, 5G, etc., or a combination thereof.
For one embodiment, one or more of the processor(s) 102 may be loaded with logic of one or more controllers (e.g., memory controller modules) of the control module 104. For one embodiment, one or more of the processor(s) 102 may be loaded together with logic of one or more controllers of the control module 104 to form a system level load (SwP). For one embodiment, one or more of the processor(s) 102 may be integrated on the same mold as logic of one or more controllers of the control module 104. For one embodiment, one or more of the processor(s) 102 may be integrated on the same die with logic of one or more controllers of the control module 104 to form a system on chip (SoC).
In various embodiments, cloud server 100 may be, but is not limited to being: cloud servers, desktop computing devices, or mobile computing devices (e.g., laptop computing devices, handheld computing devices, tablet computers, netbooks, etc.). In various embodiments, cloud server 100 may have more or fewer components and/or different architectures. For example, in some exemplary design considerations, cloud server 100 includes one or more cameras, keyboards, liquid Crystal Display (LCD) screens (including touch screen displays), non-volatile memory ports, multiple antennas, graphics chips, application Specific Integrated Circuits (ASICs), and speakers.
The foregoing has outlined rather broadly the more detailed description of embodiments of the application, wherein the principles and embodiments of the application are explained in detail using specific examples, the above examples being provided solely to facilitate the understanding of the method and core concepts of the application; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.
Claims (10)
1. An optimization method based on a prefabricated vegetable production control system, which is characterized by being applied to the cloud server, the method comprising:
Acquiring production control abnormal data of a prefabricated vegetable production control system acquired in a designated production control mode;
encoding the production control abnormal data to obtain an abnormal encoding vector;
determining a target abnormal label cluster core corresponding to the abnormal coding vector from the abnormal label cluster core data sequence based on the characteristic distance between the abnormal coding vector and the abnormal label cluster core in the abnormal label cluster core data sequence, wherein the abnormal label cluster core data sequence comprises abnormal label cluster cores of different abnormal labels, and the abnormal label cluster cores are significant abnormal vectors corresponding to abnormal production nodes of different abnormal labels;
updating the abnormal coding vector according to the target abnormal label cluster core to obtain an updated abnormal coding vector;
determining target abnormality characterization information corresponding to the production control abnormal data based on the updated abnormality coding vector;
and carrying out abnormal root cause positioning on the production control abnormal data based on the target abnormal characterization information, generating abnormal root cause positioning information, and optimizing the prefabricated vegetable production control system according to the abnormal root cause positioning information.
2. The method of optimizing a pre-made dish production control system of claim 1, further comprising:
Loading the production control abnormal data into an abnormal root cause positioning model, wherein the abnormal root cause positioning model comprises a feature encoder, an abnormal tag cluster core unit, a fusion unit and a prediction unit, and the abnormal tag cluster core unit is composed of abnormal tag cluster cores in the abnormal tag cluster core data sequence;
the encoding the production control abnormal data to obtain an abnormal encoding vector comprises the following steps:
encoding the production control abnormal data according to the characteristic encoder to obtain the abnormal encoding vector;
the determining, based on the feature distance between the anomaly coding vector and the anomaly label cluster core in the anomaly label cluster core data sequence, a target anomaly label cluster core corresponding to the anomaly coding vector from the anomaly label cluster core data sequence includes:
determining the target abnormal label cluster core corresponding to the abnormal coding vector according to the abnormal label cluster core unit; the updating of the abnormal coding vector according to the target abnormal label cluster core to obtain an updated abnormal coding vector comprises the following steps:
fusing the target abnormal label cluster core and the abnormal coding vector according to the fusion unit to generate the updated abnormal coding vector;
The determining the target abnormality characterization information corresponding to the production control abnormal data based on the updated abnormal coding vector includes:
determining the target abnormal characterization information corresponding to the production control abnormal data based on the updated abnormal coding vector according to the fusion unit;
the abnormal root cause positioning of the production control abnormal data based on the target abnormal characterization information, generating abnormal root cause positioning information, includes:
and carrying out abnormal root cause positioning on the production control abnormal data based on the target abnormal characterization information according to the prediction unit, and generating abnormal root cause positioning information.
3. The optimization method based on a prepared dish production control system according to claim 2, further comprising constructing the abnormal tag cluster core unit, the constructing the abnormal tag cluster core unit comprising:
in the process of carrying out model weight parameter iterative updating on the abnormal root cause positioning model, encoding the abnormal data of the template production control according to the characteristic encoder, and generating a reference abnormal encoding vector of an abnormal production node marked by an abnormal label attribute, wherein the abnormal label attribute represents an abnormal label of the abnormal production node included in the abnormal data of the template production control;
Updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the reference abnormal coding vector of the abnormal production node.
4. The optimization method based on the prefabricated dish production control system according to claim 3, wherein updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the reference abnormal encoding vector of the abnormal production node comprises:
if the abnormal label cluster core of the abnormal label which the abnormal production node belongs to is an empty set, taking the reference abnormal coding vector of the abnormal production node as the abnormal label cluster core of the abnormal label which the abnormal production node belongs to;
if the abnormal label cluster core of the abnormal label which the abnormal production node belongs to is not an empty set, calculating the characteristic distance between the reference abnormal coding vector of the abnormal production node and the abnormal label cluster core of the abnormal label which the abnormal production node belongs to;
updating an abnormal label cluster center of an abnormal label to which the abnormal production node belongs in the abnormal label cluster center unit based on the characteristic distance;
the updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the characteristic distance comprises the following steps:
If the characteristic distance is greater than or equal to the threshold distance, adding the reference abnormal coding vector of the abnormal production node into an abnormal label cluster center of an abnormal label to which the abnormal production node belongs;
the updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the characteristic distance comprises the following steps:
if the characteristic distance is larger than or equal to the threshold distance, determining the number relation between the number of the abnormal label cluster centers of the abnormal labels of the abnormal production nodes and the threshold number;
and updating the abnormal label cluster core of the abnormal label to which the abnormal production node belongs in the abnormal label cluster core unit based on the quantity relation.
5. A method of optimizing a control system based on prepared dish production according to claim 3, wherein said constructing said abnormal tag cluster core unit comprises:
constructing a target training cost value based on the difference between the abnormal tag attribute and the obtained reference updated abnormal coding vector;
updating the abnormal label cluster core in the abnormal label cluster core unit based on the target training cost value so as to optimize the abnormal label cluster core unit.
6. The optimization method based on a prefabricated dish production control system according to any one of claims 1-5, wherein the determining, based on the feature distance between the anomaly encoding vector and the anomaly tag cluster center in the anomaly tag cluster center data sequence, a target anomaly tag cluster center corresponding to the anomaly encoding vector from the anomaly tag cluster center data sequence corresponds to different anomaly tag cluster center data sequences under different designated production control modes, includes:
acquiring an abnormal label cluster core data sequence corresponding to the appointed production control mode; and determining the target abnormal label cluster center corresponding to the abnormal coding vector from the abnormal label cluster center data sequence corresponding to the appointed production control mode.
7. The optimization method based on a pre-dish production control system of any one of claims 1-5, wherein the determining, based on the updated anomaly encoding vector, target anomaly characterization information corresponding to the production control anomaly data comprises:
and fusing the updated abnormal coding vector and the abnormal coding vector to generate the target abnormal characterization information.
8. The optimizing method based on a prefabricated dish production control system according to any one of claims 1 to 5, wherein updating the anomaly encoding vector according to the target anomaly tag cluster core to obtain an updated anomaly encoding vector comprises:
Calculating a characteristic distance measurement array based on the target abnormal label cluster cores and the abnormal coding vectors, wherein array members in the characteristic distance measurement array represent weight values of each target abnormal label cluster core to the abnormal coding vectors;
and carrying out weighted summation on the target abnormal label cluster core and the abnormal coding vector based on the characteristic distance measurement array, and generating the updated abnormal coding vector corresponding to the abnormal coding vector.
9. A method of optimizing a preparation-based control system according to any one of claims 1-8, characterized in that the method further comprises:
acquiring template production control abnormal data under a reference production control mode, wherein the template production control abnormal data has an abnormal label attribute of an abnormal production node included in the template production control abnormal data;
loading the template production control abnormal data into an initialization abnormal root cause positioning model, wherein the initialization abnormal root cause positioning model comprises an initial feature encoder, an initial abnormal label cluster core unit, an initial fusion unit and an initial prediction unit, and the template production control abnormal data has an abnormal label attribute of an abnormal production node included in the template production control abnormal data;
Coding the template production control abnormal data according to the initial characteristic coder to obtain a reference abnormal coding vector;
determining a target reference abnormal label cluster center corresponding to the reference abnormal code vector from the initial abnormal label cluster center unit based on the characteristic distance between the reference abnormal code vector and the abnormal label cluster center in the abnormal label cluster center data sequence according to the initial abnormal label cluster center unit;
updating the reference abnormal coding vector by utilizing the target reference abnormal label cluster core according to the initial fusion unit to obtain a reference updated abnormal coding vector; determining target reference anomaly characterization information corresponding to the template production control anomaly data based on the reference update anomaly coding vector according to the initial fusion unit;
according to the initial prediction unit, performing abnormal root cause positioning on the production control abnormal data based on the target reference abnormal characterization information, and generating reference abnormal root cause positioning information;
and carrying out model weight parameter iterative updating on the initialized abnormal root cause positioning model according to the abnormal label attribute and the reference abnormal root cause positioning information to generate the abnormal root cause positioning model.
10. The optimizing system based on the prefabricated vegetable production control system is characterized by comprising a cloud server and the prefabricated vegetable production control system in communication connection with the cloud server, wherein the cloud server is specifically used for:
acquiring production control abnormal data of a prefabricated vegetable production control system acquired in a designated production control mode;
encoding the production control abnormal data to obtain an abnormal encoding vector;
determining a target abnormal label cluster core corresponding to the abnormal coding vector from the abnormal label cluster core data sequence based on the characteristic distance between the abnormal coding vector and the abnormal label cluster core in the abnormal label cluster core data sequence, wherein the abnormal label cluster core data sequence comprises abnormal label cluster cores of different abnormal labels, and the abnormal label cluster cores are significant abnormal vectors corresponding to abnormal production nodes of different abnormal labels;
updating the abnormal coding vector according to the target abnormal label cluster core to obtain an updated abnormal coding vector;
determining target abnormality characterization information corresponding to the production control abnormal data based on the updated abnormality coding vector;
And carrying out abnormal root cause positioning on the production control abnormal data based on the target abnormal characterization information, generating abnormal root cause positioning information, and optimizing the prefabricated vegetable production control system according to the abnormal root cause positioning information.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310696098.8A CN116594364A (en) | 2023-06-13 | 2023-06-13 | Optimization method and system based on prefabricated vegetable production control system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310696098.8A CN116594364A (en) | 2023-06-13 | 2023-06-13 | Optimization method and system based on prefabricated vegetable production control system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116594364A true CN116594364A (en) | 2023-08-15 |
Family
ID=87589973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310696098.8A Pending CN116594364A (en) | 2023-06-13 | 2023-06-13 | Optimization method and system based on prefabricated vegetable production control system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116594364A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116962673A (en) * | 2023-09-21 | 2023-10-27 | 四川君恒泰电子电器有限公司 | Abnormality detection method and system applied to intelligent television main board system |
| CN117369426A (en) * | 2023-12-08 | 2024-01-09 | 台昌树脂(佛山)有限公司 | State monitoring method and system based on hot melt adhesive production control system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101971278B1 (en) * | 2018-12-13 | 2019-04-26 | 주식회사 알고리고 | Anomaly detection apparatus using artificial neural network |
| CN109766393A (en) * | 2018-12-06 | 2019-05-17 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| CN111913848A (en) * | 2020-07-24 | 2020-11-10 | 上海泛微网络科技股份有限公司 | Data monitoring and analyzing method and related equipment |
| CN112817814A (en) * | 2021-01-21 | 2021-05-18 | 网思科技股份有限公司 | Abnormity monitoring method, system, storage medium and electronic device |
| CN114048055A (en) * | 2021-11-09 | 2022-02-15 | 上海哔哩哔哩科技有限公司 | Time series data abnormal root cause analysis method and system |
-
2023
- 2023-06-13 CN CN202310696098.8A patent/CN116594364A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109766393A (en) * | 2018-12-06 | 2019-05-17 | 中科恒运股份有限公司 | Abnormal deviation data examination method and device |
| KR101971278B1 (en) * | 2018-12-13 | 2019-04-26 | 주식회사 알고리고 | Anomaly detection apparatus using artificial neural network |
| CN111913848A (en) * | 2020-07-24 | 2020-11-10 | 上海泛微网络科技股份有限公司 | Data monitoring and analyzing method and related equipment |
| CN112817814A (en) * | 2021-01-21 | 2021-05-18 | 网思科技股份有限公司 | Abnormity monitoring method, system, storage medium and electronic device |
| CN114048055A (en) * | 2021-11-09 | 2022-02-15 | 上海哔哩哔哩科技有限公司 | Time series data abnormal root cause analysis method and system |
Non-Patent Citations (1)
| Title |
|---|
| 吕思才;张格;张耀方;刘红日;王子博: "一种面向工控系统的PU学习入侵检测方法", 信息安全学报 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116962673A (en) * | 2023-09-21 | 2023-10-27 | 四川君恒泰电子电器有限公司 | Abnormality detection method and system applied to intelligent television main board system |
| CN116962673B (en) * | 2023-09-21 | 2023-12-15 | 四川君恒泰电子电器有限公司 | Abnormality detection method and system applied to intelligent television main board system |
| CN117369426A (en) * | 2023-12-08 | 2024-01-09 | 台昌树脂(佛山)有限公司 | State monitoring method and system based on hot melt adhesive production control system |
| CN117369426B (en) * | 2023-12-08 | 2024-03-01 | 台昌树脂(佛山)有限公司 | State monitoring method and system based on hot melt adhesive production control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116594364A (en) | Optimization method and system based on prefabricated vegetable production control system | |
| CN110866925B (en) | Method and device for image segmentation | |
| CN112232495A (en) | Prediction model training method, device, medium and computing equipment | |
| CN111079944A (en) | Method and device for realizing interpretation of transfer learning model, electronic equipment and storage medium | |
| CN113723618A (en) | SHAP optimization method, equipment and medium | |
| CN116542673B (en) | Fraud identification method and system applied to machine learning | |
| WO2022012233A1 (en) | Method and computing apparatus for quantification calibration, and computer-readable storage medium | |
| CN116433050B (en) | Abnormality alarm method and system applied to agricultural big data management system | |
| CN116797973A (en) | Data mining method and system applied to sanitation intelligent management platform | |
| CN113822144A (en) | Target detection method and device, computer equipment and storage medium | |
| CN116108697B (en) | Acceleration test data processing method, device and equipment based on multiple performance degradation | |
| CN111046085B (en) | Data tracing processing method and device, medium and equipment | |
| US20230022253A1 (en) | Fast and accurate prediction methods and systems based on analytical models | |
| CN116303100B (en) | File integration test method and system based on big data platform | |
| CN111598121A (en) | Cabinet equipment detection method | |
| CN116563278B (en) | Detection result display method, device, computer equipment and storage medium | |
| WO2023087234A1 (en) | Artificial intelligence (ai) -assisted context-aware pipeline creation | |
| CN115481562B (en) | Multi-parallelism optimization method and device, recognition method and electronic equipment | |
| CN113112008B (en) | Method, apparatus and computer readable storage medium for neural network data quantization | |
| CN113111997B (en) | Method, apparatus and related products for neural network data quantization | |
| WO2021017546A1 (en) | Neural network quantization method and apparatus, chip, electronic device and board card | |
| CN117291609A (en) | Data analysis method and system for account risk monitoring system | |
| CN112396170B (en) | Operation method, device, computer equipment and storage medium | |
| CN116977936A (en) | Intelligent monitoring method and system for sanitation garbage classification delivery points | |
| CN117312826A (en) | Data analysis method and system for power grid line loss repair system |
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 |