CN115030885A - Air compressor machine all-in-one - Google Patents
Air compressor machine all-in-one Download PDFInfo
- Publication number
- CN115030885A CN115030885A CN202210632382.4A CN202210632382A CN115030885A CN 115030885 A CN115030885 A CN 115030885A CN 202210632382 A CN202210632382 A CN 202210632382A CN 115030885 A CN115030885 A CN 115030885A
- Authority
- CN
- China
- Prior art keywords
- value
- air compressor
- path
- abnormal
- trigger
- 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.)
- Granted
Links
- 230000002159 abnormal effect Effects 0.000 claims abstract description 113
- 238000001514 detection method Methods 0.000 claims abstract description 41
- 238000012544 monitoring process Methods 0.000 claims abstract description 20
- 230000005856 abnormality Effects 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 claims description 81
- 238000004088 simulation Methods 0.000 claims description 29
- 238000012549 training Methods 0.000 claims description 23
- 238000011156 evaluation Methods 0.000 claims description 21
- 230000000694 effects Effects 0.000 claims description 20
- 238000013210 evaluation model Methods 0.000 claims description 12
- 238000000034 method Methods 0.000 claims description 10
- 230000003828 downregulation Effects 0.000 claims description 8
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 238000013507 mapping Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 abstract description 4
- 230000009286 beneficial effect Effects 0.000 description 10
- 230000017525 heat dissipation Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 239000002023 wood Substances 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000002222 downregulating effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000020169 heat generation Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B49/00—Control, e.g. of pump delivery, or pump pressure of, or safety measures for, machines, pumps, or pumping installations, not otherwise provided for, or of interest apart from, groups F04B1/00 - F04B47/00
- F04B49/06—Control using electricity
- F04B49/065—Control using electricity and making use of computers
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B51/00—Testing machines, pumps, or pumping installations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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)
- Theoretical Computer Science (AREA)
- Mechanical Engineering (AREA)
- Software Systems (AREA)
- Medical Informatics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Physics & Mathematics (AREA)
- Computing Systems (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Computer Hardware Design (AREA)
- Control Of Positive-Displacement Pumps (AREA)
Abstract
The invention provides an air compressor integrated machine, which comprises: an air compressor body; the operation monitoring unit is arranged in the air compressor body; the controller is arranged in the air compressor body and is in communication connection with the operation monitoring unit; the controller obtains operation data of the operation monitoring unit for monitoring the operation of the first air compressor, detects the abnormal operation of the first air compressor according to the operation data, and outputs an abnormal detection result. The air compressor all-in-one machine disclosed by the invention has the advantages that manual inspection is not needed, the labor cost is reduced, in addition, the abnormality detection has comprehensiveness and timeliness, and larger faults caused by abnormal expansion are avoided.
Description
Technical Field
The invention relates to the technical field of air compressors, in particular to an air compressor all-in-one machine.
Background
At present, the air compressors may have abnormalities (such as abnormal heat dissipation and exhaust pressure) in the operation process, the abnormalities are generally found by manual inspection, the labor cost is high, in addition, a plurality of air compressors are used in the production of general enterprises, the manual inspection is not necessarily timely and comprehensive, the abnormalities are possibly expanded, and larger faults are caused;
therefore, a solution is needed.
Disclosure of Invention
The invention provides an air compressor all-in-one machine which does not need manual inspection, reduces the labor cost, has comprehensiveness and timeliness in abnormality detection, and avoids larger faults caused by abnormal expansion.
The invention provides an air compressor integrated machine, which comprises:
an air compressor body;
at least one operation monitoring unit arranged in the air compressor body;
the controller is arranged in the air compressor body and is in communication connection with the operation monitoring unit;
the controller obtains operation data of the operation monitoring unit for monitoring the operation of the first air compressor, detects the abnormal operation of the first air compressor according to the operation data, and outputs an abnormal detection result.
Preferably, the controller performs the following operations:
and training an operation abnormity detection model, and detecting the operation abnormity of the first air compressor according to the operation data based on the operation abnormity detection model.
Preferably, training the operation abnormality detection model includes:
acquiring a plurality of air compressor abnormal event sets, wherein the air compressor abnormal event sets comprise: a plurality of first events;
acquiring first equipment information of a second air compressor corresponding to the first event;
acquiring second equipment information of the first air compressor;
extracting information elements of the first device information to obtain a plurality of first elements;
extracting information elements of the second device information to obtain a plurality of second elements;
matching the first element with the second element to obtain matching degree of matching;
if the matching degree is greater than or equal to a preset matching degree threshold value, acquiring the element type of the first element or the second element for matching;
acquiring an abnormal type of the first event, and acquiring a preset element category-matching degree-value degree library corresponding to the abnormal type;
determining a value degree which corresponds to the matching degree and the element category together based on the element category-matching degree-value degree library, and associating the value degree with the corresponding first event;
accumulating and calculating the value degree associated with the first event to obtain a value degree sum;
if the sum of the value degrees is larger than or equal to a preset value degree and a preset threshold value, taking the corresponding first event as a second event;
integrating the second events to obtain a training sample;
and performing model training according to the training samples based on a preset model training algorithm to obtain an abnormal operation detection model.
Preferably, acquiring a plurality of air compressor abnormal event sets includes:
acquiring a preset air compressor abnormal event set to acquire a path set, wherein the air compressor abnormal event set acquisition path set comprises: a plurality of first paths;
obtaining a path category of the first path, wherein the path category comprises: an inner path and an outer path;
when the path type of the first path is an internal path, taking the corresponding first path as a first target to be acquired;
when the path type of the first path is an external path, acquiring a credit value corresponding to the first path;
if the credit value is greater than or equal to a preset credit value threshold value, taking the corresponding first path as a second target to be acquired;
otherwise, acquiring a guarantee value corresponding to the first path;
if the guarantee value is larger than or equal to a preset guarantee value threshold value, taking the corresponding first path as a third target to be acquired;
and acquiring the air compressor abnormal event set through the first target to be acquired, the second target to be acquired and the third target to be acquired respectively.
Preferably, the obtaining of the credit value corresponding to the first path includes:
determining at least one second path associated with the first path based on a preset associated path library;
acquiring at least one credit record corresponding to the first path and the second path;
and performing credit evaluation on the first path according to the credit record based on a preset credit evaluation model to obtain a credit value of the first path, and finishing the acquisition.
Preferably, the obtaining of the guarantee value corresponding to the first path includes:
acquiring a guarantee condition record of the first path;
and performing guarantee evaluation on the first path based on a preset guarantee evaluation model to obtain a guarantee value of the first path, and finishing the acquisition.
Preferably, the controller performs the following operations:
when the abnormal detection result contains at least one first abnormal item, constructing an abnormal item-processing strategy library, determining a first processing strategy corresponding to the first abnormal item based on the abnormal item-processing strategy library, and performing corresponding processing on the first abnormal item based on the first processing strategy.
Preferably, constructing an outlier-processing strategy library comprises:
acquiring a preset abnormal item set, wherein the abnormal item set comprises: a plurality of second anomaly terms;
acquiring a plurality of alternative second processing strategies corresponding to the second abnormal items;
obtaining an effect value of the second processing strategy, and if the effect value is greater than or equal to a preset effect value threshold, taking the second processing strategy as a third processing strategy;
acquiring a preset air compressor simulation operation model, and performing simulation configuration on the air compressor simulation operation model according to the operation data;
after the simulation configuration is completed, mapping the second abnormal item into the air compressor simulation operation model to obtain a third abnormal item;
performing simulation processing on the third exception item based on the third processing strategy;
in the processing process of the simulation processing, effect evaluation is carried out on the processing process based on a preset effect evaluation model, an evaluation value is obtained, a preset first weight coefficient is given to the evaluation value, a first target value is obtained and is associated with the corresponding third processing strategy, meanwhile, conflict recognition is carried out on the processing process based on a preset conflict recognition model, a conflict value is obtained, a preset second weight coefficient is given to the conflict value, a second target value is obtained and is associated with the corresponding third processing strategy;
accumulating and calculating the first target value and the second target value associated with the third processing strategy to obtain a target value sum;
pairing and combining the maximum target value and the corresponding third processing strategy with the corresponding second abnormal item to obtain a pairing and combining item;
constructing an abnormal item-processing strategy library based on each pairing combination item.
Preferably, the controller performs the following operations:
dynamically determining target data corresponding to the latest preset time period from the operation data;
splitting the target data into a plurality of first data items, and meanwhile, acquiring a generation time point corresponding to the first data items;
establishing a time axis, and correspondingly arranging the first data item on the time axis based on the generation time point;
performing data feature extraction on the first data item to obtain a plurality of first features;
acquiring a preset trigger feature library, matching the first feature with a second feature in the trigger feature library, if the first feature is matched with the second feature in the trigger feature library, taking the second feature matched with the first feature as a third feature, and simultaneously taking the corresponding first data item as a second data item;
obtaining a trigger type corresponding to the third feature, where the trigger type includes: individual triggering and chain triggering;
when the trigger type corresponding to the third feature is single trigger, acquiring a first trigger value corresponding to the third feature;
when the trigger type corresponding to the third feature is a chained trigger, acquiring at least one chained trigger item corresponding to the third feature, where the chained trigger item includes: a chain triggering direction, a chain triggering range and a fourth characteristic of chain triggering;
determining the first data item corresponding to the interlink trigger range in the interlink trigger direction of the second data item on the time axis as a third data item;
performing feature extraction on the third data item to obtain a plurality of fifth features, matching the fifth features with the fourth features, and if the matching is in accordance with the fourth features, obtaining a second trigger value corresponding to the fourth features in accordance with the matching;
accumulating and calculating the first trigger value and the second trigger value to obtain a trigger value sum;
and adjusting the detection time interval for carrying out operation abnormity detection on the first air compressor based on the sum of the trigger values.
Preferably, adjusting a detection time interval for detecting the abnormal operation of the first air compressor based on the sum of the trigger values includes:
acquiring a preset time interval initial value;
acquiring the trigger value and a corresponding down-regulation strategy;
and correspondingly adjusting the initial value of the time interval downwards based on the downwards adjusting strategy.
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 schematic diagram of an air compressor integrated machine in the embodiment of the 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 invention provides an air compressor integrated machine, as shown in figure 1, comprising:
an air compressor body 1;
at least one operation monitoring unit 2 arranged in the air compressor body 1;
the controller 3 is arranged in the air compressor body 1 and is in communication connection with the operation monitoring unit 2;
the controller 3 acquires operation data of the operation monitoring unit 2 for performing operation monitoring on the first air compressor, performs operation abnormality detection on the first air compressor according to the operation data, and outputs an abnormality detection result.
The working principle and the beneficial effects of the technical scheme are as follows:
the operation monitoring unit 2 can be a temperature sensor for monitoring the operation temperature in the air compressor body 1, can be a pressure sensor for monitoring the pressure condition in the air compressor body 1, and can also be a flow sensor for monitoring the outlet flow in the outlet pipe of the air compressor body 1; controller 3 detects the unusual operation of first air compressor machine according to the operation data, need not the manual work and inspects, has reduced the human cost, and in addition, the unusual detection possesses comprehensiveness and promptness, avoids unusual the expansion to cause bigger trouble.
The invention provides an air compressor all-in-one machine, wherein a controller 3 executes the following operations:
and training an operation abnormity detection model, and detecting the operation abnormity of the first air compressor according to the operation data based on the operation abnormity detection model.
The working principle and the beneficial effects of the technical scheme are as follows:
when the first air compressor is detected to be abnormal according to the operation data, an abnormal operation detection model is trained, and the first air compressor is detected to be abnormal according to the operation data based on the abnormal operation detection model.
The invention provides an air compressor integrated machine, which trains an abnormal operation detection model and comprises the following components:
acquiring a plurality of air compressor abnormal event sets, wherein the air compressor abnormal event sets comprise: a plurality of first events;
acquiring first equipment information of a second air compressor corresponding to the first event;
acquiring second equipment information of the first air compressor;
extracting information elements of the first device information to obtain a plurality of first elements;
extracting information elements of the second device information to obtain a plurality of second elements;
matching the first element with the second element to obtain matching degree of matching;
if the matching degree is greater than or equal to a preset matching degree threshold value, acquiring the element type of the first element or the second element for matching;
acquiring an abnormal type of the first event, and acquiring a preset element category-matching degree-value degree library corresponding to the abnormal type;
determining a value degree which corresponds to the matching degree and the element category together based on the element category-matching degree-value degree library, and associating the value degree with the corresponding first event;
accumulating and calculating the value degree associated with the first event to obtain a value degree sum;
if the sum of the value degrees is larger than or equal to a preset value degree and a preset threshold value, taking the corresponding first event as a second event;
integrating the second events to obtain a training sample;
and performing model training according to the training samples based on a preset model training algorithm to obtain an abnormal operation detection model.
The working principle and the beneficial effects of the technical scheme are as follows:
in training the operation abnormity detection model, a large number of records of abnormity of the air compressor can be learned based on a machine learning technology, so that the capability of detecting the operation abnormity of the air compressor is obtained, model training is carried out, and therefore a first event (the record of abnormity of the air compressor) is obtained; however, because the second air compressor corresponding to the first event is different from the first air compressor in operation duration, maintenance records, model numbers, fault records and the like, the first event does not necessarily occur on the first air compressor, and the value screening of the first event is required; respectively extracting first equipment information (operation duration, maintenance record, model, fault record and the like) of a second air compressor and a first element and a second element of second equipment information (the same as the first equipment information) of the first air compressor, and matching to obtain a matching degree; if the matching degree is greater than or equal to a preset matching degree threshold, indicating that equipment information matching exists, acquiring a corresponding element type (such as a certain dimension record), acquiring an abnormal type (such as heat dissipation abnormality) of a first event, acquiring an element type-matching degree-value degree library (including value degrees corresponding to different matching degrees corresponding to different element types, wherein the larger the matching degree is, the larger the value degree is), determining the value degree based on the library, and indicating that the corresponding first event has learning value the larger the value degree is; accumulating and calculating the value degree associated with the first event to obtain a value degree sum; and if the sum of the value degrees is greater than or equal to the preset value degree and the threshold value, taking the corresponding second event as a training sample, and performing model training according to the training sample based on a preset model training algorithm (such as a machine learning algorithm) to obtain an abnormal operation detection model.
The invention provides an air compressor integrated machine, which obtains a plurality of air compressor abnormal event sets and comprises the following steps:
acquiring a preset air compressor abnormal event set to acquire a path set, wherein the air compressor abnormal event set acquisition path set comprises: a plurality of first paths;
obtaining a path category of the first path, the path category including: an inner path and an outer path;
when the path category of the first path is an internal path, taking the corresponding first path as a first target to be acquired;
when the path type of the first path is an external path, acquiring a credit value corresponding to the first path;
if the credit value is greater than or equal to a preset credit value threshold value, taking the corresponding first path as a second target to be acquired;
otherwise, acquiring a guarantee value corresponding to the first path;
if the guarantee value is larger than or equal to a preset guarantee value threshold value, taking the corresponding first path as a third target to be acquired;
and acquiring the air compressor abnormal event set through the first target to be acquired, the second target to be acquired and the third target to be acquired respectively.
The working principle and the beneficial effects of the technical scheme are as follows:
when an air compressor abnormal event set is obtained, setting a plurality of air compressor abnormal event set obtaining paths, namely a first path, wherein the first path corresponds to a company using an air compressor, and carrying out air compressor abnormal event sharing; the path category of the first path is divided into an internal path (company itself) and an external path (other companies using air compressors), and when the path category is the internal path, the first path is directly used as a first target to be acquired without verification; when the path type is an external path, the corresponding first path needs credit verification to obtain a corresponding credit value, the larger the credit value is, the truer and more reliable the abnormal event of the air compressor provided by the first path in history is, and if the credit value is greater than or equal to a preset credit value threshold, the corresponding first path can be used as a second target to be obtained; if not (the credit value is less than the threshold value of the credit value), the first path needs to be guaranteed, a guarantee value is obtained, the greater the guarantee value is, the greater the guaranteed degree is, and when the guarantee value is greater than or equal to the preset guarantee value threshold value, the corresponding first path can be used as a third target to be obtained; and acquiring the air compressor abnormal event set through the first target to be acquired, the second target to be acquired and the third target to be acquired respectively.
The invention provides an air compressor all-in-one machine, which acquires a credit value corresponding to a first path and comprises the following steps:
determining at least one second path associated with the first path based on a preset associated path library;
acquiring at least one credit record corresponding to the first path and the second path;
and performing credit evaluation on the first path according to the credit record based on a preset credit evaluation model to obtain a credit value of the first path, and finishing the acquisition.
The working principle and the beneficial effects of the technical scheme are as follows:
when the credit value of the first path is acquired, the credit condition of the first path needs to be judged, when the credit value is judged, a related path library is set, a second path related to the first path is determined (for example, the paths belong to the same company are related to each other), and based on the credit records of the first path and the second path (the real reliability records of the air compressor abnormal events provided historically), the credit evaluation is carried out on the first path according to a credit evaluation model (a model trained in advance for carrying out credit evaluation), so that the credit value is acquired; therefore, when a certain path generates bad credit, the related path is also affected, the cost for generating bad credit is increased, and the generation rate of generating bad credit is indirectly reduced.
The invention provides an air compressor integrated machine, which acquires a guarantee value corresponding to a first path and comprises the following steps:
acquiring a guarantee condition record of the first path;
and performing guarantee evaluation on the first path based on a preset guarantee evaluation model to obtain a guarantee value of the first path, and finishing the acquisition.
The working principle and the beneficial effects of the technical scheme are as follows:
when the first path is to be guaranteed, it is necessary to determine the guaranteed state of the first path, and when the first path is to be guaranteed, a record of the guaranteed state of the first path (for example, a certain guarantor guarantees the path, and the guarantor may be a guaranty institution or the like) is acquired, and the first path is guaranteed and evaluated based on a preset guarantee evaluation model (a model trained in advance for guarantee evaluation) to acquire the guaranteed value.
The invention provides an air compressor all-in-one machine, wherein a controller 3 executes the following operations:
when the abnormal detection result contains at least one first abnormal item, constructing an abnormal item-processing strategy library, determining a first processing strategy corresponding to the first abnormal item based on the abnormal item-processing strategy library, and performing corresponding processing on the first abnormal item based on the first processing strategy.
The working principle and the beneficial effects of the technical scheme are as follows:
when a first abnormal item (for example, abnormal heat dissipation) is detected, an optimal first processing strategy (for example, restarting the radiator for multiple times in a short time, stopping running if the radiator fails to restart, reminding workers) is determined based on the constructed abnormal item-processing strategy library, and the first abnormal item is correspondingly processed.
The invention provides an air compressor all-in-one machine, which constructs an abnormal item-processing strategy library and comprises the following steps:
obtaining a preset abnormal item set, wherein the abnormal item set comprises: a plurality of second anomaly terms;
acquiring a plurality of alternative second processing strategies corresponding to the second abnormal items;
obtaining an effect value of the second processing strategy, and if the effect value is greater than or equal to a preset effect value threshold, taking the second processing strategy as a third processing strategy;
acquiring a preset air compressor simulation operation model, and performing simulation configuration on the air compressor simulation operation model according to the operation data;
after the simulation configuration is completed, mapping the second abnormal item into the air compressor simulation operation model to obtain a third abnormal item;
performing simulation processing on the third exception item based on the third processing strategy;
in the processing process of the simulation processing, effect evaluation is carried out on the processing process based on a preset effect evaluation model, an evaluation value is obtained, a preset first weight coefficient is given to the evaluation value, a first target value is obtained and is associated with the corresponding third processing strategy, meanwhile, conflict recognition is carried out on the processing process based on a preset conflict recognition model, a conflict value is obtained, a preset second weight coefficient is given to the conflict value, a second target value is obtained and is associated with the corresponding third processing strategy;
accumulating and calculating the first target value and the second target value associated with the third processing strategy to obtain a target value sum;
pairing and combining the maximum target value and the corresponding third processing strategy with the corresponding second abnormal item to obtain a pairing and combining item;
constructing an abnormal item-processing strategy library based on each pairing combination item.
The working principle and the beneficial effects of the technical scheme are as follows:
constructing an abnormal item-processing strategy library, wherein an optimal processing strategy needs to be selected for a second abnormal item which is possible to be abnormal of the air compressor; acquiring a plurality of second processing strategies of second abnormal item candidates, and firstly, based on an effect value, removing the second processing strategies with poor effects; secondly, some second processing strategies may not be suitable for processing the operation condition of the current air compressor (for example, the processing strategies are immediate shutdown, heat generation is reduced, and heat dissipation burden is reduced, but if the air compressor is in high-speed operation, some internal components such as a piston and the like need to be manually reset after sudden shutdown, and are relatively complicated), so that it is required to determine to eliminate the remaining third processing strategies, which are suitable for the processing strategies adopted when the first abnormal item occurs under the operation condition of the current first air compressor, to obtain a preset air compressor simulation operation model (corresponding to the simulation model of the air compressor), and perform simulation configuration on the preset air compressor simulation operation model according to operation data to realize simulation operation; after the simulation configuration, mapping the second abnormal item in a simulation operation model of the air compressor (simulating the occurrence of the second abnormal item in the model), obtaining a third abnormal item, and performing simulation processing on the third abnormal item based on a third processing strategy; performing effect evaluation based on a preset effect evaluation model (a model trained in advance for evaluating the effect of the treatment), and obtaining an evaluation value (positive value); performing conflict recognition (for example, recognizing that the air compressor runs at a high speed, and some internal components such as a piston and the like need to be manually reset after sudden shutdown) based on a preset conflict recognition model (a model which is trained in advance and is used for recognizing and processing conflicts), and acquiring a conflict value (negative value); respectively endowing a preset first weight for an evaluation value and a preset second weight for a conflict value (multiplying when endowing weights), performing accumulation calculation to obtain a target value sum, pairing and combining the maximum target value sum and a corresponding third processing strategy with a second abnormal item, and constructing a database; the construction quality of the abnormal item-processing strategy library is improved to a great extent, and the suitability of the processing strategy determined based on the abnormal item-processing strategy library is ensured.
The invention provides an air compressor all-in-one machine, wherein a controller 3 executes the following operations:
dynamically determining target data corresponding to the latest preset time period from the operation data;
splitting the target data into a plurality of first data items, and acquiring a generation time point corresponding to the first data items;
establishing a time axis, and correspondingly arranging the first data item on the time axis based on the generation time point;
performing data feature extraction on the first data item to obtain a plurality of first features;
acquiring a preset trigger feature library, matching the first feature with a second feature in the trigger feature library, if the first feature is matched with the second feature in the trigger feature library, taking the second feature matched with the first feature as a third feature, and simultaneously taking the corresponding first data item as a second data item;
obtaining a trigger type corresponding to the third feature, where the trigger type includes: individual triggering and chain triggering;
when the trigger type corresponding to the third feature is single trigger, acquiring a first trigger value corresponding to the third feature;
when the trigger type corresponding to the third feature is a catenated trigger, acquiring at least one catenated trigger corresponding to the third feature, where the catenated trigger includes: a chain triggering direction, a chain triggering range and a fourth characteristic of chain triggering;
determining the first data item corresponding to the interlink trigger range in the interlink trigger direction of the second data item on the time axis as a third data item;
extracting features of the third data item to obtain a plurality of fifth features, matching the fifth features with the fourth features, and if the fifth features match with the fourth features, obtaining a second trigger value corresponding to the fourth features which match with the fourth features;
accumulating and calculating the first trigger value and the second trigger value to obtain a trigger value sum;
and adjusting the detection time interval for carrying out operation abnormity detection on the first air compressor based on the sum of the trigger values.
The working principle and the beneficial effects of the technical scheme are as follows:
in order to save power consumption, the detection time interval for detecting the abnormal operation of the first air compressor needs to be adjusted in a self-adaptive manner; dynamically determining the wood newspaper data corresponding to the latest preset time period (for example, 100 seconds) from the operation data, splitting the wood newspaper data into first data items, arranging the first data items on a time axis, extracting first characteristics, matching the first characteristics with second characteristics in a preset trigger characteristic library (storing operation data characteristics suspected to be abnormal), if the first characteristics are matched with the second characteristics, obtaining a trigger type corresponding to a third characteristic matched with the third characteristics, wherein the trigger type is divided into an independent trigger (when one suspected characteristic is matched with the corresponding characteristic, the trigger type can represent that the air compressor is possibly abnormal) and a combined trigger (when a plurality of suspected characteristic interlink matching symbols are matched, the trigger type can represent that the air compressor is possibly abnormal), when the trigger type is an independent trigger, obtaining a corresponding first trigger value, wherein the larger the first trigger value is, the larger the possibility of the occurrence of the abnormality is, and when the trigger type is an interlink trigger, the further supplement confirmation is required, acquiring a corresponding catenated trigger item, wherein the catenated trigger item comprises a catenated trigger direction (for example: after), a catenated trigger range (for example: within 3 seconds) and a fourth characteristic of catenated trigger, determining a third data item based on the catenated trigger direction and the catenated trigger range, extracting a fifth characteristic, matching the fifth characteristic with the fourth characteristic, confirming the catenated trigger if the fifth characteristic is matched with the fourth characteristic, acquiring a corresponding second trigger value, and the larger the second trigger value is, the higher the possibility of abnormity is; accumulating and calculating a first trigger value and a second trigger value to obtain a trigger value sum; and adjusting the detection time interval for carrying out operation abnormity detection on the first air compressor based on the sum of the trigger values.
The invention provides an air compressor all-in-one machine, which adjusts the detection time interval for carrying out operation abnormity detection on a first air compressor based on the sum of trigger values, and comprises the following steps:
acquiring a preset time interval initial value;
acquiring the trigger value and a corresponding down-regulation strategy;
and correspondingly adjusting the initial value of the time interval downwards based on the downwards adjusting strategy.
The working principle and the beneficial effects of the technical scheme are as follows:
the time interval initial value may be 3 seconds; acquiring a trigger value and a corresponding down-regulation strategy, wherein the larger the trigger value sum is, the larger the total possibility of abnormity of the air compressor is, the larger the down-regulation degree of the down-regulation strategy is, and correspondingly down-regulating the time interval initial value based on the down-regulation strategy;
the detection time interval for detecting the abnormal operation of the first air compressor can be adjusted based on the sum of the trigger values through the following formula:
wherein, the first and the second end of the pipe are connected with each other,
for the initial value of the time interval after the down-regulation,
and sigma is the trigger value and gamma is a preset relation coefficient which can be set by a worker.
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 (10)
1. The utility model provides an air compressor machine all-in-one which characterized in that includes:
an air compressor body;
at least one operation monitoring unit arranged in the air compressor body;
the controller is arranged in the air compressor body and is in communication connection with the operation monitoring unit;
the controller obtains operation data of the operation monitoring unit for monitoring the operation of the first air compressor, detects the abnormal operation of the first air compressor according to the operation data, and outputs an abnormal detection result.
2. The integrated air compressor-compressor machine of claim 1, wherein the controller performs the following operations:
and training an operation abnormity detection model, and detecting the operation abnormity of the first air compressor according to the operation data based on the operation abnormity detection model.
3. The air compressor all-in-one machine as claimed in claim 2, wherein the training of the abnormal operation detection model comprises:
acquiring a plurality of air compressor abnormal event sets, wherein the air compressor abnormal event sets comprise: a plurality of first events;
acquiring first equipment information of a second air compressor corresponding to the first event;
acquiring second equipment information of the first air compressor;
extracting information elements of the first device information to obtain a plurality of first elements;
extracting information elements of the second device information to obtain a plurality of second elements;
matching the first element with the second element to obtain matching degree of matching;
if the matching degree is greater than or equal to a preset matching degree threshold value, acquiring the element type of the first element or the second element for matching;
acquiring an abnormal type of the first event, and acquiring a preset element category-matching degree-value degree library corresponding to the abnormal type;
determining a value degree which corresponds to the matching degree and the element category together based on the element category-matching degree-value degree library, and associating the value degree with the corresponding first event;
accumulating and calculating the value degree associated with the first event to obtain a value degree sum;
if the sum of the value degrees is larger than or equal to a preset value degree and a preset threshold value, taking the corresponding first event as a second event;
integrating the second events to obtain a training sample;
and performing model training according to the training samples based on a preset model training algorithm to obtain an abnormal operation detection model.
4. The air compressor all-in-one machine of claim 3, wherein the step of obtaining a plurality of air compressor abnormal event sets comprises the steps of:
acquiring a preset air compressor abnormal event set to acquire a path set, wherein the air compressor abnormal event set acquisition path set comprises: a plurality of first paths;
obtaining a path category of the first path, the path category including: an inner path and an outer path;
when the path type of the first path is an internal path, taking the corresponding first path as a first target to be acquired;
when the path type of the first path is an external path, acquiring a credit value corresponding to the first path;
if the credit value is greater than or equal to a preset credit value threshold value, taking the corresponding first path as a second target to be acquired;
otherwise, acquiring a guarantee value corresponding to the first path;
if the guarantee value is larger than or equal to a preset guarantee value threshold value, taking the corresponding first path as a third target to be acquired;
and acquiring an air compressor abnormal event set through the first target to be acquired, the second target to be acquired and the third target to be acquired respectively.
5. The air compressor/compressor machine of claim 4, wherein obtaining a credit value corresponding to the first path comprises:
determining at least one second path associated with the first path based on a preset associated path library;
acquiring at least one credit record corresponding to the first path and the second path;
and performing credit evaluation on the first path according to the credit record based on a preset credit evaluation model to obtain a credit value of the first path, and finishing the acquisition.
6. The integrated air compressor-compressor machine of claim 4, wherein obtaining a warranty value corresponding to the first path comprises:
acquiring a guarantee condition record of the first path;
and performing guarantee evaluation on the first path based on a preset guarantee evaluation model to obtain a guarantee value of the first path, and finishing the acquisition.
7. The integrated air compressor-compressor machine of claim 1, wherein the controller performs the following operations:
when the abnormal detection result contains at least one first abnormal item, constructing an abnormal item-processing strategy library, determining a first processing strategy corresponding to the first abnormal item based on the abnormal item-processing strategy library, and performing corresponding processing on the first abnormal item based on the first processing strategy.
8. The integrated air compressor-compressor machine of claim 1, wherein the constructing of the abnormal item-processing strategy library comprises:
acquiring a preset abnormal item set, wherein the abnormal item set comprises: a plurality of second anomaly terms;
acquiring a plurality of alternative second processing strategies corresponding to the second abnormal items;
obtaining an effect value of the second processing strategy, and if the effect value is greater than or equal to a preset effect value threshold, taking the second processing strategy as a third processing strategy;
acquiring a preset air compressor simulation operation model, and performing simulation configuration on the air compressor simulation operation model according to the operation data;
after the simulation configuration is completed, mapping the second abnormal item into the air compressor simulation operation model to obtain a third abnormal item;
performing simulation processing on the third exception item based on the third processing strategy;
in the processing process of simulation processing, effect evaluation is carried out on the processing process based on a preset effect evaluation model, an evaluation value is obtained, a preset first weight coefficient is given to the evaluation value, a first target value is obtained and is associated with the corresponding third processing strategy, meanwhile, conflict recognition is carried out on the processing process based on a preset conflict recognition model, a conflict value is obtained, a preset second weight coefficient is given to the conflict value, a second target value is obtained and is associated with the corresponding third processing strategy;
accumulating and calculating the first target value and the second target value associated with the third processing strategy to obtain a target value sum;
pairing and combining the maximum target value and the corresponding third processing strategy with the corresponding second abnormal item to obtain a pairing and combining item;
constructing an abnormal item-processing strategy library based on each of the paired combined items.
9. The air compressor all-in-one machine as claimed in claim 1, wherein the controller performs the following operations:
dynamically determining target data corresponding to the latest preset time period from the operation data;
splitting the target data into a plurality of first data items, and meanwhile, acquiring a generation time point corresponding to the first data items;
establishing a time axis, and correspondingly arranging the first data item on the time axis based on the generation time point;
performing data feature extraction on the first data item to obtain a plurality of first features;
acquiring a preset trigger feature library, matching the first feature with a second feature in the trigger feature library, if the first feature is matched with the second feature in the trigger feature library, taking the second feature matched with the first feature as a third feature, and simultaneously taking the corresponding first data item as a second data item;
obtaining a trigger type corresponding to the third feature, where the trigger type includes: individual triggering and chain triggering;
when the trigger type corresponding to the third feature is single trigger, acquiring a first trigger value corresponding to the third feature;
when the trigger type corresponding to the third feature is a chained trigger, acquiring at least one chained trigger item corresponding to the third feature, where the chained trigger item includes: a chain triggering direction, a chain triggering range and a fourth characteristic of chain triggering;
determining the first data item corresponding to the interlink trigger range in the interlink trigger direction of the second data item on the time axis as a third data item;
extracting features of the third data item to obtain a plurality of fifth features, matching the fifth features with the fourth features, and if the fifth features match with the fourth features, obtaining a second trigger value corresponding to the fourth features which match with the fourth features;
accumulating and calculating the first trigger value and the second trigger value to obtain a trigger value sum;
and adjusting the detection time interval for carrying out operation abnormity detection on the first air compressor based on the sum of the trigger values.
10. The air compressor integrated machine of claim 9, wherein adjusting a detection time interval for detecting an operation abnormality of the first air compressor based on the sum of the trigger values comprises:
acquiring a preset time interval initial value;
acquiring the trigger value and a corresponding down-regulation strategy;
and correspondingly adjusting the initial value of the time interval downwards based on the downwards adjusting strategy.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210632382.4A CN115030885B (en) | 2022-06-06 | 2022-06-06 | Air compressor machine all-in-one |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210632382.4A CN115030885B (en) | 2022-06-06 | 2022-06-06 | Air compressor machine all-in-one |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115030885A true CN115030885A (en) | 2022-09-09 |
| CN115030885B CN115030885B (en) | 2023-12-26 |
Family
ID=83123314
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210632382.4A Active CN115030885B (en) | 2022-06-06 | 2022-06-06 | Air compressor machine all-in-one |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115030885B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003021072A (en) * | 2001-07-03 | 2003-01-24 | Anest Iwata Corp | Air compressor, and group control air compressing system using it |
| JP2014040953A (en) * | 2012-08-22 | 2014-03-06 | Mitsubishi Electric Corp | Freezing air conditioner |
| CN203756531U (en) * | 2014-03-18 | 2014-08-06 | 重庆埃泰克能源科技有限公司 | Air compressor controller |
| CN109630388A (en) * | 2018-11-23 | 2019-04-16 | 广东艾高装备科技有限公司 | Operation method, storage medium, air compressor machine and the operating system of air compressor machine |
| CN112766396A (en) * | 2021-01-27 | 2021-05-07 | 昆仑数智科技有限责任公司 | System, method, computer device and medium for detecting device abnormality |
| US20210293239A1 (en) * | 2018-07-10 | 2021-09-23 | Hitachi Industrial Equipment Systems Co., Ltd. | Compressor and Monitoring System |
| CN113847232A (en) * | 2021-07-28 | 2021-12-28 | 合肥工业大学 | Air compressor cluster operation adjusting method and system based on cloud edge cooperation |
| CN114165474A (en) * | 2022-02-11 | 2022-03-11 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus and computer storage medium for detecting a fault condition of an air compressor |
| CN114542444A (en) * | 2022-01-18 | 2022-05-27 | 江苏日易能源科技有限公司 | Intelligent monitoring method and system for air compressor |
-
2022
- 2022-06-06 CN CN202210632382.4A patent/CN115030885B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003021072A (en) * | 2001-07-03 | 2003-01-24 | Anest Iwata Corp | Air compressor, and group control air compressing system using it |
| JP2014040953A (en) * | 2012-08-22 | 2014-03-06 | Mitsubishi Electric Corp | Freezing air conditioner |
| CN203756531U (en) * | 2014-03-18 | 2014-08-06 | 重庆埃泰克能源科技有限公司 | Air compressor controller |
| US20210293239A1 (en) * | 2018-07-10 | 2021-09-23 | Hitachi Industrial Equipment Systems Co., Ltd. | Compressor and Monitoring System |
| CN109630388A (en) * | 2018-11-23 | 2019-04-16 | 广东艾高装备科技有限公司 | Operation method, storage medium, air compressor machine and the operating system of air compressor machine |
| CN112766396A (en) * | 2021-01-27 | 2021-05-07 | 昆仑数智科技有限责任公司 | System, method, computer device and medium for detecting device abnormality |
| CN113847232A (en) * | 2021-07-28 | 2021-12-28 | 合肥工业大学 | Air compressor cluster operation adjusting method and system based on cloud edge cooperation |
| CN114542444A (en) * | 2022-01-18 | 2022-05-27 | 江苏日易能源科技有限公司 | Intelligent monitoring method and system for air compressor |
| CN114165474A (en) * | 2022-02-11 | 2022-03-11 | 蘑菇物联技术（深圳）有限公司 | Method, apparatus and computer storage medium for detecting a fault condition of an air compressor |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115030885B (en) | 2023-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107111309B (en) | Gas turbine fault prediction using supervised learning methods | |
| US8509985B2 (en) | Detecting anomalies in fault code settings and enhancing service documents using analytical symptoms | |
| EP3055747B1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| US5625574A (en) | Method and data processing system for monitoring operating states of a technical plant | |
| US20110264424A1 (en) | Apparatus abnormality diagnosis method and system | |
| EP3055746B1 (en) | Correlation and annotation of time series data sequences to extracted or existing discrete data | |
| CN107111311A (en) | Utilize the combustion gas turbine Transducer fault detection of sparse coding method | |
| US8751423B2 (en) | Turbine performance diagnostic system and methods | |
| CN107765658A (en) | A kind of compressor control method based on Internet of Things, apparatus and system | |
| WO2015121176A1 (en) | Method of identifying anomalies | |
| GB2476246A (en) | Diagnosing an operation mode of a machine | |
| EP3944043B1 (en) | Maintenance work assistance device | |
| CN111678699B (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN116382217A (en) | Intelligent operation and maintenance monitoring system for production line | |
| CN103699514A (en) | Method for detecting steady state and judging operation condition of water treatment process in thermal power plant | |
| CN108153987A (en) | A kind of hydraulic pump Multiple faults diagnosis approach based on the learning machine that transfinites | |
| US8271233B2 (en) | Method of multi-level fault isolation design | |
| CN112711850A (en) | Unit online monitoring method based on big data | |
| CN117932322B (en) | Flour equipment fault diagnosis method and system | |
| US20120166151A1 (en) | System and method for performance monitoring of commercial refrigeration | |
| CN116720048A (en) | Power station auxiliary machine fault diagnosis method and system based on machine learning model | |
| CN113554128B (en) | Unconventional anomaly detection method and system and storage medium | |
| CN115030885A (en) | Air compressor machine all-in-one | |
| CN108958220B (en) | Intelligent instrument configuration software and method of fluid machinery measurement and control system | |
| CN116802471A (en) | Method and system for comprehensively diagnosing defects of rotary machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |