CN114091280B

CN114091280B - Method and device for detecting stability of heat preservation system of graphitization furnace

Info

Publication number: CN114091280B
Application number: CN202111419668.6A
Authority: CN
Inventors: 郭志军; 杨兰贺; 陈瑶; 宋宾宾; 吴建祥
Original assignee: Jiangsu Hanhua Heat Management Technology Co ltd
Current assignee: Jiangsu Hanhua Heat Management Technology Co ltd
Priority date: 2021-11-26
Filing date: 2021-11-26
Publication date: 2022-07-05
Anticipated expiration: 2041-11-26
Also published as: CN114091280A

Abstract

The invention provides a method and a device for detecting the stability of a heat preservation system of a graphitization furnace, wherein the method comprises the following steps: step S1: arranging a proper temperature monitoring network in a heat insulation system of the graphitization furnace; step S2: constructing a stability detection project library suitable for a temperature monitoring network, acquiring an optimal selection rule, and selecting a corresponding first stability detection project from the stability detection project library based on the optimal selection rule; step S3: extracting target monitoring data corresponding to a first stability detection item from a temperature monitoring network, and meanwhile, acquiring a preset stability analysis model corresponding to the first stability detection item; step S4: and inputting the target monitoring data into the stability analysis model, obtaining a stability analysis result and outputting the stability analysis result. According to the method and the device for detecting the stability of the heat insulation system of the graphitization furnace, the worker does not need to judge according to experience, and the accurate judgment on the stability of the heat insulation performance of the heat insulation mechanism is realized.

Description

Method and device for detecting stability of heat insulation system of graphitizing furnace

Technical Field

The invention relates to the technical field of temperature monitoring, in particular to a method and a device for detecting the stability of a heat insulation system of a graphitization furnace.

Background

At present, in order to keep the temperature inside the graphitization furnace stable for a long time, a layer of heat preservation mechanism (such as a heat preservation plate, a heat insulation plate, a heat collection plate and the like) is usually wrapped on the outer surface of a furnace body of the graphitization furnace, but the heat preservation performance of the heat preservation mechanism is not accurate enough when being judged by experience of workers (for example, observing the temperature change in the furnace), and the heat preservation performance of the heat preservation mechanism is not accurate enough when being judged by experience alone along with the increase of the service time of the heat preservation mechanism;

therefore, a solution is needed.

Disclosure of Invention

One of the purposes of the invention is to provide a method and a device for detecting the stability of a heat insulation system of a graphitization furnace, which can automatically arrange a proper temperature monitoring network, select a proper stability detection project, detect the stability and output a detection result, and do not need workers to judge by experience, thereby realizing accurate judgment of the stability of the heat insulation performance of a heat insulation mechanism.

The embodiment of the invention provides a method for detecting the stability of a heat insulation system of a graphitization furnace, which comprises the following steps:

step S1: arranging a proper temperature monitoring network in a heat insulation system of the graphitization furnace;

step S2: constructing a stability detection project library suitable for the temperature monitoring network, acquiring an optimal selection rule, and selecting a corresponding first stability detection project from the stability detection project library based on the optimal selection rule;

step S3: extracting target monitoring data corresponding to the first stability detection item from the temperature monitoring network, and meanwhile, acquiring a preset stability analysis model corresponding to the first stability detection item;

step S4: and inputting the target monitoring data into the stability analysis model, obtaining a stability analysis result and outputting the stability analysis result.

Preferably, the step S1: a temperature monitoring network disposed appropriately within a thermal insulation system of a graphitization furnace comprising:

acquiring a plurality of first heat preservation system unstable events;

acquiring a provider corresponding to the unstable event of the first thermal insulation system, and acquiring a provision type of the provider for providing the unstable event of the first thermal insulation system, where the provision type includes: active provision and passive provision;

when the providing type of the first heat preservation system unstable event provided by the provider is active providing, obtaining a providing flow of the first heat preservation system unstable event provided by the provider;

splitting the providing flow into a plurality of first flows, and simultaneously, performing feature extraction on the first flows to obtain a plurality of first features;

acquiring a preset sensitive feature library, matching the first feature with a first sensitive feature in the sensitive feature library, if the first feature matches with the first sensitive feature in the sensitive feature library, taking the matched first sensitive feature as a second sensitive feature, and simultaneously taking the corresponding first process as a second process;

acquiring a process executing process for executing the second process when the provider provides the first heat preservation system unstable event;

performing feature extraction on the process execution process to obtain a plurality of second features;

obtaining verification information corresponding to the second sensitive feature, wherein the verification information includes: a first feature processing mode, a demand degree corresponding to the first feature processing mode and a confirmation feature library;

summarizing the demand degrees corresponding to the same first characteristic processing mode to obtain a sum of the demand degrees;

if the sum of the demand degrees is larger than or equal to a preset demand degree and a preset threshold value, taking the corresponding first feature processing mode as a second feature processing mode;

processing the second features based on the second feature processing mode to obtain a plurality of features to be confirmed;

merging the confirmation feature libraries to obtain a confirmation feature total library;

matching the feature to be confirmed with a first confirmation feature in the confirmation feature total library, and if the matching is in accordance with the first confirmation feature, taking the first confirmation feature in accordance with the matching as a second confirmation feature;

obtaining an influence value corresponding to the second confirmation feature;

summarizing all the influence values to obtain influence value sums;

if the sum of the influence values is larger than or equal to a preset influence value and a preset threshold value, rejecting the corresponding unstable event of the first heat preservation system;

when the providing type of the first heat preservation system unstable event provided by the provider is passive providing, acquiring a first experience value corresponding to a collector passively collecting the first heat preservation system unstable event, and acquiring a guarantee value corresponding to the provider;

if the first empirical value is less than or equal to a preset first empirical value threshold and/or the guarantee value is less than or equal to a preset guarantee value threshold, rejecting the corresponding first heat preservation system instability event;

when the first heat preservation system unstable events needing to be removed are all removed, the remaining first heat preservation system unstable events are removed to serve as second heat preservation system unstable events;

extracting occurrence information in the second insulation system instability event, wherein the occurrence information comprises: at least one occurrence cause, a weight corresponding to the occurrence cause, and a first occurrence point;

determining a second occurrence point position corresponding to the first occurrence point position in the heat preservation system;

acquiring attribute information of the heat preservation system and operation information of the graphitization furnace;

acquiring a preset point location instability probability prediction model, inputting at least one occurrence reason corresponding to the same first occurrence point location, weight corresponding to the occurrence reason, attribute information and operation information into the point location instability probability prediction model, and acquiring instability probability corresponding to the second occurrence point location;

if the instability probability is larger than or equal to a preset instability probability threshold value, triggering a first temperature monitoring instrument corresponding to the second occurrence point to be started;

and the first temperature monitoring instruments which are triggered to be started form a temperature monitoring network to complete the layout.

Preferably, in step S2, constructing a stability detection item library suitable for the temperature monitoring network includes:

acquiring a preset stability detection item set, wherein the stability detection item set comprises: a plurality of second stability check items;

determining whether the second stability detection item relates to the first temperature monitoring instrument triggered to be started in the temperature monitoring network, and if so, taking the corresponding second stability detection item as a third stability detection item;

acquiring a preset first blank database, and inputting the third stability detection item into the first blank database;

and when the third stability detection items needing to be input into the first blank database are all input, taking the first blank database as a stability detection item library to finish construction.

Preferably, in step S2, the obtaining an optimal selection rule includes:

acquiring the instability probability of the second occurrence point position corresponding to at least one first temperature monitoring instrument triggered to be started in the temperature monitoring network related to the third stability detection item, and summarizing to obtain a ranking value;

setting an optimal selection rule, wherein the optimal selection rule comprises the following steps: and selecting the corresponding third stability detection item from large to small according to the ranking value.

Preferably, the method for detecting the stability of the heat preservation system of the graphitization furnace further comprises the following steps:

step S5: constructing a point location association library, when the stability analysis result contains an unstable third occurrence point location, determining a fourth occurrence point location associated with the third occurrence point location based on the point location association library, determining a second temperature monitoring instrument corresponding to the fourth occurrence point location, confirming whether the temperature monitoring network contains the second temperature monitoring instrument, and if not, supplementing the second temperature monitoring instrument into the temperature monitoring network;

the point location association library is constructed, and the method comprises the following steps:

acquiring a point location set corresponding to the heat preservation system, wherein the point location set comprises: a plurality of fifth point of occurrence;

randomly selecting one unstable event of the second heat preservation system, and taking the unstable event as an unstable event of a third heat preservation system;

randomly selecting another unstable event of the second heat preservation system, and taking the event as an unstable event of a fourth heat preservation system;

acquiring a preset preliminary association confirmation model, and inputting the unstable event of the third heat insulation system and the unstable event of the fourth heat insulation system into the preliminary association confirmation model to acquire a first confirmation degree;

if the first certainty degree is greater than or equal to a preset certainty degree threshold value, determining a sixth occurrence point in the fifth occurrence points corresponding to the first occurrence point in the occurrence information in the third insulation system unstable event, and simultaneously determining a seventh occurrence point in the fifth occurrence points corresponding to the first occurrence point in the occurrence information in the fourth insulation system unstable event;

setting and issuing deep association confirmation test items, wherein the deep association confirmation test items comprise: the sixth and seventh point of occurrence;

obtaining a plurality of deep association confirmation test records corresponding to the deep association confirmation items, wherein the deep association confirmation test records comprise: at least one tester, an adopted test strategy and a second confirmation degree obtained by the test;

acquiring a second experience value of the tester, and acquiring the strategy weight of the test strategy;

acquiring a preset confirmation index calculation model, and inputting the second empirical value, the strategy weight and the second confirmation degree into the confirmation index calculation model to obtain a confirmation index;

if the confirmation index is larger than or equal to a preset confirmation index threshold value, taking the deep association confirmation test item as an association combination;

acquiring a preset second blank database, and inputting the association combination into the second blank database;

and when the association combinations needing to be input into the second blank database are all input, taking the second blank database as a point location association database to finish construction.

The embodiment of the invention provides a system for detecting the stability of a heat insulation system of a graphitization furnace, which comprises:

the layout module is used for arranging a proper temperature monitoring network in a heat insulation system of the graphitization furnace;

the selection module is used for constructing a stability detection project library suitable for the temperature monitoring network, acquiring an optimal selection rule, and selecting a corresponding first stability detection project from the stability detection project library based on the optimal selection rule;

the extraction module is used for extracting target monitoring data corresponding to the first stability detection item from the temperature monitoring network and acquiring a preset stability analysis model corresponding to the first stability detection item;

and the input module is used for inputting the target monitoring data into the stability analysis model, obtaining a stability analysis result and outputting the stability analysis result.

Preferably, the layout module performs the following operations:

obtaining a plurality of first heat preservation system unstable events;

acquiring a provider corresponding to the first heat-preservation system unstable event, and acquiring a provision type of the provider for providing the first heat-preservation system unstable event, wherein the provision type comprises: active provision and passive provision;

obtaining an influence value corresponding to the second confirmation feature;

summarizing the influence values to obtain a sum of the influence values;

Preferably, the selecting module performs the following operations:

acquiring a preset stability detection item set, wherein the stability detection item set comprises: a plurality of second stability detection items;

confirming whether the second stability detection item relates to the first temperature monitoring instrument triggered to be started in the temperature monitoring network, and if so, taking the corresponding second stability detection item as a third stability detection item;

Preferably, the selecting module performs the following operations:

Preferably, graphitizing furnace heat preservation system stability detection device still includes:

the supplementing module is used for constructing a point location association library, determining a fourth occurrence point location associated with a third occurrence point location based on the point location association library when the stability analysis result contains an unstable third occurrence point location, determining a second temperature monitoring instrument corresponding to the fourth occurrence point location, confirming whether the temperature monitoring network contains the second temperature monitoring instrument, and supplementing the second temperature monitoring instrument into the temperature monitoring network if the temperature monitoring network does not contain the second temperature monitoring instrument;

the supplementing module executes the following operations:

acquiring a preset preliminary association confirmation model, and inputting the third heat insulation system unstable event and the fourth heat insulation system unstable event into the preliminary association confirmation model to acquire a first confirmation degree;

Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.

The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.

Drawings

The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:

FIG. 1 is a flow chart of a method for detecting the stability of a heat insulation system of a graphitization furnace in an embodiment of the present invention;

FIG. 2 is a flowchart of a method for detecting the stability of a thermal insulation system of a graphitization furnace in accordance with another embodiment of the present invention;

fig. 3 is a schematic diagram of a system for detecting stability of a heat preservation system of a graphitization furnace in an embodiment of the present invention.

Detailed Description

The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.

The embodiment of the invention provides a method for detecting the stability of a heat insulation system of a graphitization furnace, which comprises the following steps of:

The working principle and the beneficial effects of the technical scheme are as follows:

arranging a proper temperature monitoring network in a heat insulation system (heat insulation mechanism) of the graphitizing furnace (the point position of the temperature monitoring instrument required to be arranged in the heat insulation mechanism is triggered and started by the corresponding temperature monitoring instrument); constructing a stability detection item library suitable for the temperature monitoring network (constructing a stability detection item corresponding to a point position triggering the starting of a temperature monitoring instrument, such as heat preservation stability detection of a certain area on the left side of the furnace); acquiring an optimal selection rule (preferentially selecting stability detection items detected to be insufficient in thermal insulation stability), and selecting a first stability detection item based on the optimal selection rule; extracting monitoring data corresponding to a first stability detection project from a temperature monitoring network (what point position the first stability detection project relates to and what temperature monitoring instrument is required to extract the monitoring data corresponding to the temperature monitoring instrument), inputting the monitoring data into a preset stability analysis model corresponding to the first stability detection project (different stability detection projects correspond to a matched stability analysis model which is generated after a machine learning algorithm is utilized to learn analysis records of thermal insulation stability analysis of a large number of workers aiming at the monitoring data corresponding to different stability detection projects), and obtaining a stability analysis result (for example, the stability analysis result is that the thermal insulation stability of a certain area on the left side of the furnace is poor, and workers can repair the area);

according to the embodiment of the invention, a proper temperature monitoring network can be automatically distributed, a proper stability detection project is selected for stability detection, and a detection result is output, so that the accurate judgment of the stability of the heat preservation performance of the heat preservation mechanism is realized without the judgment of workers by experience, meanwhile, a local area with insufficient heat preservation performance can be positioned, and the problem that the judgment is more accurate by experience alone due to the fact that the heat preservation performance of the heat preservation mechanism is partially insufficient along with the increase of the service time of the heat preservation mechanism is solved.

The embodiment of the invention provides a method for detecting the stability of a heat insulation system of a graphitization furnace, which comprises the following steps of S1: a temperature monitoring network disposed within a thermal insulation system of a graphitization furnace comprising:

obtaining a plurality of first heat preservation system unstable events;

obtaining verification information corresponding to the second sensitive feature, wherein the verification information comprises: a first feature processing mode, a demand degree corresponding to the first feature processing mode and a confirmation feature library;

obtaining an influence value corresponding to the second confirmation feature;

summarizing all the influence values to obtain influence value sums;

acquiring a plurality of first heat-preservation-system unstable events (event records when heat preservation performance of the graphitization furnace is unstable by other manufacturers using the graphitization furnace with the same model); the method includes the steps that a provider (a certain manufacturer) provides a first heat preservation system unstable event, and the type of the first heat preservation system unstable event is divided into active provision (actively sends the first heat preservation system unstable event to an acquirer, however, point-to-point one-by-one sending is complicated, and generally, corresponding links are disclosed after the first heat preservation system unstable event is uploaded to a certain cloud end to be acquired by the acquirer) and passive provision (the manufacturer does not necessarily need to actively provide for no compensation, the acquirer sets a collector, goes to a corresponding factory to negotiate, and collects the first heat preservation system unstable event); when a provider provides the providing type of the first heat preservation system unstable event as active providing, acquiring a providing flow (for example, uploading to a certain cloud and disclosing a corresponding link), splitting the providing flow into a plurality of first flows, and extracting a first characteristic; matching the first characteristic with a first sensitive characteristic in a preset sensitive characteristic library (comprising a database which provides a large number of characteristics with risks in the process, for example, the sensitive characteristic is that an unstable event of the heat preservation system is uploaded to an unauthorized cloud storage platform), and if the first characteristic is matched with the first sensitive characteristic, the first sensitive characteristic has risks corresponding to a second process; acquiring a process execution process (specific execution record) of a provider executing a second process, and extracting a second characteristic; acquiring verification information corresponding to the matched and conformed second sensitive characteristics, wherein the verification information comprises a first characteristic processing mode (for example, if the second sensitive characteristics indicate that if a provider generates combined characteristics of two steps of 'granting unauthorized cloud storage platform modification permission' and 'cloud storage platform generating modification operation', an uploaded heat preservation system unstable event is possibly tampered, so that the characteristic processing mode is a characteristic combination, all characteristics are combined to see whether the characteristics of the two steps exist or not), a corresponding demand degree (a constant is obtained, the larger the demand degree is, the more necessary the characteristic processing mode is), and a confirmation characteristic library (for example, the combined characteristics of the two steps of 'granting unauthorized cloud storage platform modification permission' and 'cloud storage platform generating modification operation'); summarizing (summing) the demand degrees corresponding to the same first feature processing mode to obtain a demand degree sum, wherein if the demand degree sum is greater than or equal to a preset demand degree sum threshold (constant), the second feature processing mode corresponding to the second feature is necessary to be processed; because the risk indicated by the second sensitive feature does not necessarily exist in the corresponding process execution process, and the provider may execute in another process execution process, all the second features are processed based on the second feature processing mode for the comprehensiveness of the security verification, and a plurality of features to be confirmed are obtained; merging the confirmation feature libraries to obtain a confirmation feature total library; matching the features to be confirmed with the first confirmation features in the confirmation feature master library, if the matching is in accordance with the first confirmation features, acquiring an influence value corresponding to the second confirmation features which are in accordance with the matching (the larger the influence value is, the larger the risk of acquiring an unstable event corresponding to the first heat preservation system is), summarizing (summing and calculating) the influence value, and acquiring a sum of the influence values; if the sum of the influence values is greater than or equal to the preset influence and threshold (constant), the acquisition risk is high, and the corresponding first heat preservation system unstable event is removed to ensure the safety and the accuracy of the acquired first heat preservation system unstable event; when the providing type is passive providing, acquiring a first experience value of a collector (the greater the experience value is, the greater the comprehensiveness and accuracy of the collector in collecting the first insulation system unstable event) and, at the same time, acquiring a guarantee value of a provider (the greater the guarantee value is, the greater the cost is for making mistakes by the provider) [ for example, the greater the cost is for providing the false first insulation system unstable event ]; if the first checked value is smaller and/or the guarantee value is smaller and is not credible, rejecting the corresponding first heat preservation system unstable event; after all the events are removed, extracting and removing occurrence information in the rest second heat-preservation system unstable events, wherein the occurrence information comprises an occurrence reason (for example, the use time is long, the performance of a heat-preservation material is reduced), the weight of the occurrence reason (the larger the weight is, the larger the degree of the second heat-preservation system unstable event caused by the occurrence reason is), and a first occurrence point (a certain position of a heat-preservation mechanism of the graphitization furnace); determining a second occurrence point position corresponding to the first occurrence point position in the heat preservation system; acquiring attribute information of a heat preservation system (material type, repair record, material quantity and the like of a heat preservation material) and operation information of the graphitization furnace (operation duration, operation internal temperature change and the like); inputting at least one occurrence reason corresponding to the same first occurrence point location, and weight, attribute information and operation information corresponding to the occurrence reasons into the point location instability probability prediction model (a model generated by analyzing occurrence information in a large number of artificially different heat preservation system instability events, attributes of a self heat preservation system and operation of a graphitization furnace by using a machine learning algorithm and learning a record of the probability of the heat preservation system instability events occurring on the self heat preservation system), and obtaining the instability probability corresponding to a second occurrence point location; if the instability probability is larger, triggering a temperature monitoring instrument (such as a temperature sensor) corresponding to the second generation point to start; each temperature monitoring instrument triggered to be started forms a temperature monitoring network;

according to the embodiment of the invention, a proper temperature monitoring network is intelligently distributed in the heat insulation system of the graphitization furnace, and all temperature monitoring instruments do not need to be triggered to be started, so that the stability detection efficiency is improved, and the detection power consumption is reduced; when the temperature monitoring network layout is carried out, the temperature monitoring network layout is determined based on the unstable event of the heat preservation system, the setting is reasonable, and the proper temperature monitoring network layout can be determined no matter what using state the currently used graphitizing furnace is in; meanwhile, after the heat preservation system unstable event is obtained, based on the difference of the types provided by the provider, careful verification is respectively carried out, the heat preservation system unstable event which has risks and can not be determined in data authenticity is eliminated, the obtained safety is guaranteed, and the accuracy of the temperature monitoring network layout is improved.

The embodiment of the invention provides a method for detecting the stability of a heat insulation system of a graphitization furnace, wherein in the step S2, a stability detection item library suitable for a temperature monitoring network is constructed, and the method comprises the following steps:

when a stability detection item library suitable for the temperature monitoring network is constructed, whether a second stability detection item in a preset stability detection item set (including a set of a large number of stability detection items) relates to a first temperature monitoring instrument triggered to be started in the temperature monitoring network is determined, if yes, a corresponding third stability detection item is input into the first blank database, and therefore the stability detection item library is matched with the temperature monitoring network.

The embodiment of the invention provides a method for detecting the stability of a heat insulation system of a graphitization furnace, wherein in the step S2, the optimal selection rule is obtained, and the method comprises the following steps:

when the optimal selection rule is obtained, the instability probability of the second occurrence point position corresponding to at least one first temperature monitoring instrument triggered to be started in the temperature monitoring network related to the third stability detection item is summarized, the ranking value is obtained, the larger the ranking value is, the larger the probability that the third stability detection item detects that the heat insulation system is unstable is, the more the ranking is to be selected, the setting is reasonable, the stability detection efficiency is improved, and meanwhile, the more intelligentized is realized.

setting and issuing deep association confirmation test items, wherein the deep association confirmation test items comprise: said sixth point of occurrence and said seventh point of occurrence;

constructing a point location association library, when the third point location is unstable in heat preservation, determining a fourth point location associated with the third point location based on the point location association library, determining whether a second temperature monitoring instrument of the fourth point location is already in the temperature monitoring network, and if not, supplementing the fourth point location with the second temperature monitoring instrument, such as: the temperature of the top of the graphitizing furnace rises suddenly, and a certain third point in a heat preservation mechanism outside the top surface of the graphitizing furnace detects that the heat preservation is unstable, however, other points (a fourth point associated with the third point) of the heat preservation mechanism outside the top surface may also have heat preservation instability, a temperature monitoring network needs to be supplemented, the temperature monitoring network is updated, a corresponding optimal selection rule and a stability detection project library are also updated, the detection comprehensiveness is improved, and the actual use requirements are better met;

in addition, when a point location association library is constructed, two unstable events of a third heat preservation system and an unstable event of a fourth heat preservation system are randomly selected and input into a preset preliminary association confirmation model (a model generated after a large amount of records of the basic attributes of the unstable events of the two heat preservation systems are analyzed and preliminarily associated and confirmed by a machine learning algorithm, for example, if the occurrence points and the occurrence time of the unstable events of the two heat preservation systems are close, preliminary association is performed), and a first confirmation degree is obtained (a constant is obtained, the larger the first confirmation degree is, the higher the confirmation degree of the preliminary association is); if the first confirmation degree is larger than or equal to a preset confirmation degree threshold (constant), the preliminary association confirmation is qualified, deep association confirmation is needed, and deep association confirmation test items are set and issued (issued to testers); obtaining a plurality of deep association confirmation test records corresponding to deep association confirmation items, wherein the deep association confirmation test records comprise testers and test strategies (for example, analyzing the internal structure of a heat preservation mechanism, the performance of a heat preservation material at a certain position in the internal structure is reduced, whether the performance of the heat preservation material at the periphery of the internal structure is reduced or not, for example, analyzing the position of a heat preservation furnace to analyze the use condition of the heat preservation material, the heat dissipation speed at the periphery of the graphitization furnace is generally higher than the heat dissipation speed at the top of the graphitization furnace, so that the use condition of the heat preservation material at the periphery is different from the use condition of the heat preservation material at the top, for example, analyzing the occurrence reasons of unstable events of different heat preservation systems, and if the occurrence reasons are the same, corresponding points can be associated with each other), and obtaining a second confirmation degree (the larger the second confirmation degree is, the more the test indicates that the sixth occurrence point and the seventh occurrence point are associated with each other, namely the reduction of the heat preservation performance, the other thermal insulation performance is also reduced); acquiring a second experience value corresponding to the tester (the larger the second experience value is, the more experienced the tester is, the more credible the test result is); obtaining the strategy weight of the test strategy (the larger the strategy weight is, the more credible the test result of the test by adopting the test strategy is); inputting the second experience value, the strategy weight and the second confirmation degree into a preset confirmation index calculation model (a model generated after a large number of records which are artificially and comprehensively calculated based on the second experience value, the strategy weight and the second confirmation degree are learned by using a machine learning algorithm), obtaining a confirmation index, and if the confirmation index is greater than or equal to a preset confirmation index threshold (constant), indicating that the two can be associated, generating an association combination and inputting the association combination into a second blank database; point location association library construction is detailed, and setting is reasonable; setting a preliminary association confirmation model, firstly performing preliminary association confirmation, saving resources for association confirmation, then setting a deep association confirmation item and issuing the deep association confirmation item, determining whether the sixth occurrence point location and the seventh occurrence point location can be associated based on a deep association confirmation test record, and setting reasonably and accurately;

in addition, a calculation formula for calculating the confirmation index can be built in the confirmation index calculation model, so that the working efficiency of the system is further improved, and the built-in calculation formula is as follows:

wherein σ is the confirmation index, β_iA second degree of certainty in the ith deep association confirmation test record corresponding to the deep association confirmation item, D_i，lA second experience value, tau, of the ith test person in the ith deep association confirmation test record corresponding to the deep association confirmation item_iThe strategy weight of the test strategy in the ith deep correlation confirmation test record corresponding to the deep correlation confirmation item, gamma is the total number of the deep correlation confirmation test records corresponding to the deep correlation confirmation item, t_iThe total number mu of the testers in the ith deep correlation confirmation test record corresponding to the deep correlation confirmation item₁And mu₂The weight value is a preset weight value;

in the formula, the second empirical value D_i，lThe larger the test result, the more experienced the tester is, i.e. the second empirical value D_i，lShould be positively correlated with the confirmation index; policy weight τ_iThe larger the test result is, the more trustworthy the test result is tested with the test strategy, i.e. the strategy weight τ_iShould be positively correlated with the confirmation index; the setting is reasonable.

The embodiment of the invention provides a device for detecting the stability of a heat insulation system of a graphitization furnace, which comprises the following components:

the layout module 1 is used for arranging a proper temperature monitoring network in a heat insulation system of the graphitization furnace;

the selection module 2 is used for constructing a stability detection project library suitable for the temperature monitoring network, acquiring an optimal selection rule, and selecting a corresponding first stability detection project from the stability detection project library based on the optimal selection rule;

the extraction module 3 is configured to extract target monitoring data corresponding to the first stability detection item from the temperature monitoring network, and meanwhile, acquire a preset stability analysis model corresponding to the first stability detection item;

and the input module 4 is used for inputting the target monitoring data into the stability analysis model, obtaining a stability analysis result and outputting the stability analysis result.

The embodiment of the invention provides a device for detecting the stability of a heat insulation system of a graphitization furnace, wherein a layout module 1 executes the following operations:

obtaining a plurality of first heat preservation system unstable events;

summarizing the demand degrees corresponding to the same first characteristic processing mode to obtain a sum of demand degrees;

matching the feature to be confirmed with a first confirmation feature in the confirmation feature total library, and if the matching is in accordance, taking the first confirmation feature which is in accordance with the matching as a second confirmation feature;

obtaining an influence value corresponding to the second confirmation characteristic;

summarizing all the influence values to obtain influence value sums;

if the sum of the influence values is larger than or equal to a preset influence value and a preset threshold value, rejecting the unstable event corresponding to the first heat preservation system;

when the first heat preservation system unstable events needing to be removed are all removed, removing the remaining first heat preservation system unstable events to serve as second heat preservation system unstable events;

determining a second occurrence point corresponding to the first occurrence point in the heat preservation system;

The embodiment of the invention provides a device for detecting the stability of a heat insulation system of a graphitization furnace, wherein a selection module 2 executes the following operations:

acquiring a preset stability detection project set, wherein the stability detection project set comprises: a plurality of second stability detection items;

The embodiment of the invention provides a device for detecting the stability of a heat insulation system of a graphitization furnace, which further comprises:

the supplementing module executes the following operations:

randomly selecting one unstable event of the second heat insulation system and taking the selected unstable event as an unstable event of a third heat insulation system;

It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.

Claims

1. A method for detecting the stability of a heat insulation system of a graphitization furnace is characterized by comprising the following steps:

step S1: arranging a proper temperature monitoring network in a heat insulation system of the graphitizing furnace;

step S4: inputting the target monitoring data into the stability analysis model to obtain a stability analysis result and outputting the stability analysis result;

the step S1: a temperature monitoring network disposed within a thermal insulation system of a graphitization furnace comprising:

acquiring a plurality of first heat preservation system unstable events;

obtaining verification information corresponding to the second sensitive feature, wherein the verification information includes: a first feature processing method, a demand degree corresponding to the first feature processing method, and a confirmation feature library, the demand degree indicating a magnitude of a degree of necessity for adopting the first feature processing method, the first feature processing method including: combining the characteristics;

obtaining an influence value corresponding to the second confirmation characteristic, wherein the influence value represents the magnitude of the risk degree of obtaining the unstable event of the corresponding first heat preservation system;

summarizing all the influence values to obtain influence value sums;

when the providing type of the first heat preservation system unstable event provided by the provider is passive providing, acquiring a first experience value corresponding to a collector who passively collects the first heat preservation system unstable event, wherein the first experience value represents the degree of comprehensiveness and accuracy of the collector for collecting the first heat preservation system unstable event, and acquiring a guarantee value corresponding to the provider;

extracting occurrence information in the second insulation system instability event, wherein the occurrence information comprises: at least one occurrence cause, a weight corresponding to the occurrence cause, and a first occurrence point, the first occurrence point comprising: any point position in a heat preservation mechanism of the graphitization furnace;

if the instability probability is larger than or equal to a preset instability probability threshold, triggering a first temperature monitoring instrument corresponding to the second generation point location to be started;

2. The method for detecting the stability of the heat preservation system of the graphitization furnace as claimed in claim 1, wherein in the step S2, constructing a stability detection item library suitable for the temperature monitoring network comprises:

3. The method for detecting the stability of the heat preservation system of the graphitization furnace as claimed in claim 2, wherein in the step S2, the obtaining of the optimal selection rule comprises:

4. The method for detecting the stability of the heat preservation system of the graphitization furnace as claimed in claim 1, further comprising:

acquiring a preset preliminary association confirmation model, and inputting the third heat insulation system unstable event and the fourth heat insulation system unstable event into the preliminary association confirmation model to acquire a first confirmation degree, wherein the first confirmation degree represents the confirmation degree of preliminary association confirmation;

obtaining a plurality of deep association confirmation test records corresponding to the deep association confirmation items, wherein the deep association confirmation test records comprise: the second confirmation degree represents the confirmation degree of the sixth generation point and the seventh generation point which are related by the test;

acquiring a second experience value of the tester, wherein the second experience value represents the experience degree of the tester, and meanwhile, acquiring the strategy weight of the test strategy;

5. The utility model provides a graphitizing furnace heat preservation system stability detection device which characterized in that includes:

the input module is used for inputting the target monitoring data into the stability analysis model, obtaining a stability analysis result and outputting the stability analysis result;

the layout module performs the following operations:

obtaining a plurality of first heat preservation system unstable events;

acquiring a process executing process for executing the second process when the first heat preservation system instability event is provided by the provider;

summarizing all the influence values to obtain influence value sums;

if the first empirical value is less than or equal to a preset first empirical value threshold value and/or the guarantee value is less than or equal to a preset guarantee value threshold value, rejecting the unstable event corresponding to the first heat preservation system;

extracting occurrence information in the second heat preservation system instability event, wherein the occurrence information comprises: at least one occurrence cause, a weight corresponding to the occurrence cause, and a first occurrence point, the first occurrence point comprising: any point position in a heat preservation mechanism of the graphitization furnace;

acquiring a preset point location instability probability prediction model, and inputting at least one occurrence reason corresponding to the same first occurrence point location, weight corresponding to the occurrence reason, attribute information and operation information into the point location instability probability prediction model to acquire an instability probability corresponding to the second occurrence point location;

6. The graphitization furnace heat preservation system stability detection apparatus as recited in claim 5, wherein the selection module performs the following operations:

7. The graphitization furnace heat preservation system stability detection apparatus as recited in claim 6, wherein the selection module performs the following operations:

8. The graphitization furnace heat preservation system stability detection apparatus as recited in claim 5, further comprising:

the supplementing module executes the following operations:

acquiring a preset preliminary association confirmation model, and inputting the unstable event of the third heat insulation system and the unstable event of the fourth heat insulation system into the preliminary association confirmation model to obtain a first confirmation degree, wherein the first confirmation degree represents the confirmation degree of preliminary association confirmation;

obtaining a plurality of deep association confirmation test records corresponding to the deep association confirmation items, wherein the deep association confirmation test records comprise: the second confirmation degree represents the confirmation degree of the association between the sixth occurrence point and the seventh occurrence point in the test description;