CN114353925A - Automatic test system of SQB weighing sensor - Google Patents
Automatic test system of SQB weighing sensor Download PDFInfo
- Publication number
- CN114353925A CN114353925A CN202111671329.7A CN202111671329A CN114353925A CN 114353925 A CN114353925 A CN 114353925A CN 202111671329 A CN202111671329 A CN 202111671329A CN 114353925 A CN114353925 A CN 114353925A
- Authority
- CN
- China
- Prior art keywords
- model
- sqb
- component
- weighing sensor
- assignment
- 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
- 238000005303 weighing Methods 0.000 title claims abstract description 89
- 238000012360 testing method Methods 0.000 title claims abstract description 30
- 238000001514 detection method Methods 0.000 claims abstract description 54
- 230000002159 abnormal effect Effects 0.000 claims description 72
- 238000000034 method Methods 0.000 claims description 29
- 239000013598 vector Substances 0.000 claims description 29
- 238000010586 diagram Methods 0.000 claims description 25
- 238000013507 mapping Methods 0.000 claims description 6
- 238000003860 storage Methods 0.000 claims description 5
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000011016 integrity testing Methods 0.000 claims description 2
- 230000000007 visual effect Effects 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 5
- 238000012549 training Methods 0.000 description 5
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
Images
Landscapes
- Arrangements For Transmission Of Measured Signals (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
The invention discloses an automatic test system of an SQB weighing sensor, belonging to the technical field of weighing sensor detection and comprising a modeling module, an integrity test module and a server; the modeling module is used for establishing an integrity detection model of the SQB weighing sensor, acquiring an information graph of the SQB weighing sensor, identifying an external image component which can be collected by the SQB weighing sensor, marking the external image component as a component to be modeled, establishing a three-dimensional model of the component to be modeled according to the information graph, marking the three-dimensional model as a component model, and combining the component models according to a combination mode in the information graph to form the SQB weighing sensor model which is marked as the integrity detection model; the integrity test module is used for carrying out completeness test on the produced SQB weighing sensor, automatic detection of the integrity of the weighing sensor is achieved, the links of manual participation are greatly reduced, and the problem that the integrity detection of the weighing sensor is influenced by the experience of workers, visual angle fatigue and the like is avoided.
Description
Technical Field
The invention belongs to the technical field of weighing sensor detection, and particularly relates to an automatic test system for an SQB weighing sensor.
Background
The weighing sensors are divided into eight types, such as photoelectric type, hydraulic type, electromagnetic type, capacitance type, magnetic pole deformation type, vibration type, gyroscope type, resistance strain type and the like according to a conversion method, and the resistance strain type is used most widely; a force sensor used on a weighing sensor and a weighing apparatus, which is based on the principle of a resistance strain type weighing sensor, can convert the gravity acting on a measured object into a quantifiable output signal according to a certain proportion; after the retransmission sensor is produced and assembled, the integrity of the retransmission sensor needs to be detected, but the existing integrity detection process has a plurality of manual detection programs and has a certain detection error, so that an automatic test system of the SQB weighing sensor is needed at present and is used for solving the problems.
Disclosure of Invention
In order to solve the problems existing in the scheme, the invention provides an automatic test system of an SQB weighing sensor.
The purpose of the invention can be realized by the following technical scheme:
the automatic test system for the SQB weighing sensor comprises a modeling module, an integrity test module and a server;
the modeling module is used for establishing an integrity detection model of the SQB weighing sensor, acquiring an information diagram of the SQB weighing sensor, wherein the information diagram comprises a structure diagram and an assembly diagram, identifying an external image component which can be collected by the SQB weighing sensor, marking the external image component as a component to be modeled, establishing a three-dimensional model of the component to be modeled according to the information diagram, marking the three-dimensional model as a component model, combining the component models according to a combination mode in the information diagram to form the SQB weighing sensor model, and marking the SQB weighing sensor model as the integrity detection model;
the integrity testing module is used for carrying out completeness testing on the produced SQB weighing sensor, establishing an information acquisition model, carrying out information acquisition on the SQB weighing sensor through the information acquisition model to obtain an acquired image set, establishing an image recognition model, extracting modeling data in the acquired image set through the image recognition model, establishing the modeling model, inputting the modeling data into the modeling model, and obtaining a corresponding acquisition model; acquiring an integrity detection model, comparing the integrity detection model with an acquisition model, and acquiring abnormal parts in the acquisition model; the corresponding SQB load cell is marked as an abnormal SQB load cell.
Further, the method for establishing the information acquisition model comprises the following steps:
the method comprises the steps of matching an information acquisition scheme of the SQB weighing sensor, setting an information acquisition device according to the matched information acquisition scheme, identifying a data acquisition flow in the information acquisition scheme, establishing an information acquisition device control model according to the identified data acquisition flow, and integrating the information acquisition device and the information acquisition device control model into the information acquisition model.
Further, the method for matching the information acquisition scheme of the SQB weighing sensor comprises the following steps:
obtaining the model and the type of a weighing sensor, compiling an acquisition scheme according to the model and the type of the weighing sensor, establishing a database, storing the acquisition scheme into the database, marking the current database as an acquisition scheme library, obtaining the model of an SQB weighing sensor produced on a current production line, marking the model as a detection model, inputting the detection model into the acquisition scheme library for matching, and obtaining a corresponding information acquisition scheme.
Further, the method for comparing the integrity detection model with the collection model to obtain the abnormal component in the collection model comprises the following steps:
and obtaining the similarity between the integrity detection model and the acquisition model, marking as integral similarity, not operating when the integral similarity is not less than a threshold value X1, calculating the similarity between the integrity detection model and a corresponding component model in the acquisition model when the integral similarity is less than a threshold value X1, marking as component similarity, and marking the component model with the component similarity less than a threshold value X2 as an abnormal component.
Further, the abnormal SQB weighing sensor classifying system further comprises a classifying module, wherein the classifying module is used for classifying the abnormal SQB weighing sensor.
Further, an assignment library is established in the modeling module, assignment is carried out on component models in the SQB weighing sensor model, corresponding assignments are used as assignment labels to be associated to corresponding component models, and the current SQB weighing sensor model is marked as an integrity detection model.
Further, the method for assigning the component model in the SQB weighing sensor model comprises the following steps:
and acquiring the quantity of the component models needing assignment, selecting series numerical value assignment of corresponding kinds of quantity from an assignment library according to the acquired quantity of the component models, and corresponding representative assignment in the matched series numerical value assignment to the component models to finish assignment of the component models.
Further, the working method of the classification module comprises the following steps:
acquiring an abnormal component assignment tag corresponding to the abnormal SQB weighing sensor, acquiring component similarity corresponding to the abnormal component, identifying a distinguishing position in the abnormal component according to the component similarity, and performing serial assignment on the abnormal component according to the distinguishing position and the abnormal component assignment tag, wherein the serial assignment is marked as abnormal assignment;
acquiring a historical abnormal assignment set, vectorizing the historical abnormal assignment set, marking the vectorized historical abnormal assignment set as a historical assignment vector, mapping the historical assignment vector into a vector space, clustering the historical assignment vector in the vector space through a clustering algorithm to obtain a plurality of clusters, and setting a corresponding cluster label for each cluster;
vectorizing the obtained abnormal assignment, marking the abnormal assignment as a detection vector, mapping the detection vector to a vector space for clustering, obtaining a cluster corresponding to the detection vector, obtaining a cluster label corresponding to the cluster, marking the corresponding abnormal component with the corresponding cluster label, and sending the abnormal component to a corresponding storage position according to the distance label.
Compared with the prior art, the invention has the beneficial effects that: the automatic detection of the integrity of the weighing sensor is realized, the links of manual participation are greatly reduced, and the influence on the integrity detection of the weighing sensor caused by the problems of worker experience, visual fatigue and the like is avoided; through carrying out assignment clustering on the abnormal components and dividing the abnormal components into different categories, the abnormal components are conveniently subjected to centralized processing, the processing efficiency of the abnormal components is improved, and the economic loss is reduced.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to these drawings without creative efforts.
Fig. 1 is a schematic block diagram of the present invention.
Detailed Description
The technical solutions of the present invention will be described clearly and completely with reference to the following embodiments, and it should be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in FIG. 1, the SQB weighing sensor automatic test system comprises a modeling module, an integrity test module, a classification module and a server;
the modeling module is used for establishing an integrity detection model of the SQB weighing sensor, and the specific method comprises the following steps:
the method comprises the steps of obtaining an information diagram of the SQB weighing sensor, wherein the information diagram comprises a structural diagram and an assembly diagram, identifying an external image component which can be collected by the SQB weighing sensor and marking the external image component as a component to be modeled, wherein the component in the SQB weighing sensor can not be collected during integrity test and mainly tests appearance integrity, establishing a three-dimensional model of the component to be modeled according to the information diagram and marking the three-dimensional model as a component model, combining the component models according to a combination mode in the information diagram to form the SQB weighing sensor model, establishing an assignment library to assign the component models in the SQB weighing sensor model, associating corresponding assignments as assignment tags to the corresponding component models, and marking the current SQB weighing sensor model as an integrity detection model.
The method for establishing the assignment library comprises the following steps:
the method comprises the steps that a plurality of groups of different series of numerical value assignments are set, the numerical value assignments can be set manually, and can also be set according to the existing numerical value generation model, the same series of assignments of the series of numerical value assignments are set according to the same assignment rule, the setting rules of the different series of assignments are different, and each series of numerical value assignments has a representative assignment; establishing a database, sending the series of numerical value assignments to the database for storage, arranging a deletion unit in the database, and deleting the corresponding numerical value assignments from the database by the deletion unit after the numerical value assignments in the database are selected for use; and marking the current database as an assignment library, and acquiring a plurality of different series of numerical assignments again for storage when the number of the numerical assignments in the assignment library is lower than a preset value.
The method for assigning the component model in the SQB weighing sensor model comprises the following steps:
and acquiring the quantity of the component models needing to be assigned, selecting series numerical value assignments of corresponding types of quantities from an assignment library according to the acquired quantity of the component models, namely each component model corresponds to different series numerical value assignments, and corresponding representative assignments in the matched series numerical value assignments are corresponding to the component models to finish the assignment of the component models.
The integrity test module is used for carrying out completeness test on the produced SQB weighing sensor, and the specific method comprises the following steps:
establishing an information acquisition model, acquiring information of the SQB weighing sensor through the information acquisition model to obtain an acquired image set, establishing an image recognition model, extracting modeling data in the acquired image set through the image recognition model, establishing a modeling model, and inputting the modeling data into the modeling model to obtain a corresponding acquisition model; acquiring an integrity detection model, comparing the integrity detection model with an acquisition model, and acquiring abnormal parts in the acquisition model; the corresponding SQB load cell is marked as an abnormal SQB load cell.
The method for establishing the information acquisition model comprises the following steps:
the information acquisition scheme matched with the SQB weighing sensor is characterized in that an information acquisition device is arranged according to the matched information acquisition scheme, the information acquisition device is arranged in the information acquisition scheme, and the specific structure and components are the existing structures or devices; identifying a data acquisition flow in the information acquisition scheme, establishing an information acquisition device control model according to the identified data acquisition flow, and integrating the information acquisition device and the information acquisition device control model into the information acquisition model.
The method for matching the information acquisition scheme of the SQB weighing sensor comprises the following steps:
obtaining the model and the type of a weighing sensor, compiling an acquisition scheme according to the model and the type of the weighing sensor, establishing a database, storing the acquisition scheme into the database, marking the current database as an acquisition scheme library, obtaining the model of an SQB weighing sensor produced on a current production line, marking the model as a detection model, inputting the detection model into the acquisition scheme library for matching, and obtaining a corresponding information acquisition scheme.
The method comprises the following steps of compiling an acquisition scheme according to the model and the type of a weighing sensor by adopting a manual compiling mode, wherein the acquisition scheme is compiled according to different weighing sensors and is used for ensuring that all image information of the weighing sensors can be completely acquired, the acquisition is carried out at the designed angle and position, and the acquired information is directly converted into a three-dimensional model in order to combine with subsequent data processing; therefore, the corresponding information acquisition schemes need to be matched at an early stage.
Exemplarily, when an SQB weighing sensor enters an information acquisition model, the SQB weighing sensor is moved to a specified acquisition area to be fixed, the information acquisition device control model controls the SQB weighing sensor to move to a specified acquisition angle according to an information acquisition scheme, after the acquisition angle is reached, an image acquisition device is controlled to perform image acquisition, the image acquisition device is marked as a first acquisition image, the position of the SQB weighing sensor is adjusted according to the information acquisition scheme again, the image acquisition is performed, the image acquisition device is marked as a second acquisition image, and the like in sequence until all image acquisition set in the information acquisition scheme is completed.
The method for establishing the image recognition model comprises the following steps:
acquiring an existing initial image recognition model, wherein the initial image recognition model is an existing neural network model capable of recognizing information in images, acquiring a plurality of groups of collected image sets, setting corresponding modeling data for each group of collected image sets, integrating the collected image sets and the corresponding modeling data into a training set, retraining the initial image recognition model through the training set, and marking the initial image recognition model after successful training as an image recognition model; since each image in the captured image set is taken at a fixed angle, the extraction of the modeling data of the image recognition model is taken into account during image capture.
The modeling model is established based on a CNN network or a DNN network, and is trained by establishing a training set, wherein the training set comprises modeling data and a correspondingly set acquisition model, and the modeling model is basically fixed.
The method for comparing the integrity detection model with the acquisition model to obtain the abnormal part in the acquisition model comprises the following steps:
acquiring the similarity between the integrity detection model and the acquisition model, marking as integral similarity, not operating when the integral similarity is not less than a threshold value X1, calculating the similarity between the integrity detection model and a corresponding component model in the acquisition model when the integral similarity is less than a threshold value X1, marking as component similarity, and marking the component model with the component similarity less than a threshold value X2 as an abnormal component; both the threshold X1 and the threshold X2 were set as discussed by the expert group.
The classification module is used for classifying abnormal SQB weighing sensors, and the specific method comprises the following steps:
acquiring an abnormal component assignment tag corresponding to the abnormal SQB weighing sensor, namely the assignment tag corresponding to the component model in the integrity detection model, acquiring component similarity corresponding to the abnormal component, identifying a distinguishing position in the abnormal component according to the component similarity, wherein the distinguishing position is a place different from a normal place, and performing series assignment on the abnormal component according to the distinguishing position and the abnormal component assignment tag and marking as abnormal assignment;
acquiring a historical abnormal assignment set, vectorizing the historical abnormal assignment set, marking the vectorized historical abnormal assignment set as a historical assignment vector, mapping the historical assignment vector into a vector space, clustering the historical assignment vector in the vector space through a clustering algorithm to obtain a plurality of clusters, and setting a corresponding cluster label for each cluster, wherein the cluster label is set according to a corresponding abnormal component in the cluster;
vectorizing the obtained abnormal assignment, marking the abnormal assignment as a detection vector, mapping the detection vector to a vector space for clustering, obtaining a cluster corresponding to the detection vector, obtaining a cluster label corresponding to the cluster, marking the corresponding abnormal component with the corresponding cluster label, and sending the abnormal component to a corresponding storage position according to the distance label.
The abnormal components are assigned and clustered and are divided into different categories, so that the abnormal components are conveniently and intensively processed, and the processing efficiency of the abnormal components is improved; if the SQB weighing sensors which lack a certain same component are classified into one type, the subsequent processing and installation are facilitated.
The historical assigned vectors in the vector space are clustered by a clustering algorithm, and the existing clustering algorithm suitable for the current clustering condition, such as a K-means algorithm, can be used.
The distinctive locations in the abnormal part may be obtained according to the corresponding distinctive locations in the process of performing the similarity matching calculation.
The method for carrying out series assignment on the abnormal part according to the distinguishing position and the abnormal part assignment tag comprises the following steps:
and matching the abnormal component assignment tags in the assignment library to corresponding series numerical assignments, and selecting corresponding assignments from the series numerical assignments according to the distinguishing positions.
The working principle of the invention is as follows: the method comprises the steps of establishing an integrity detection model of the SQB weighing sensor through a modeling module, obtaining an information diagram of the SQB weighing sensor, wherein the information diagram comprises a structure diagram and an assembly diagram, identifying an external image component which can be collected by the SQB weighing sensor, marking the external image component as a component to be modeled, establishing a three-dimensional model of the component to be modeled according to the information diagram, marking the three-dimensional model as a component model, combining all the component models according to a combination mode in the information diagram to form the SQB weighing sensor model, and marking the SQB weighing sensor model as the integrity detection model;
the integrity test module is used for carrying out completeness test on the produced SQB weighing sensor, an information acquisition model is built, the information acquisition model is used for carrying out information acquisition on the SQB weighing sensor to obtain an acquired image set, an image recognition model is built, modeling data in the acquired image set are extracted through the image recognition model, the modeling model is built, and the modeling data are input into the modeling model to obtain a corresponding acquisition model; acquiring an integrity detection model, comparing the integrity detection model with an acquisition model, and acquiring abnormal parts in the acquisition model; the corresponding SQB load cell is marked as an abnormal SQB load cell.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (8)
- The automatic test system of the SQB weighing sensor is characterized by comprising a modeling module, an integrity test module and a server;the modeling module is used for establishing an integrity detection model of the SQB weighing sensor, acquiring an information diagram of the SQB weighing sensor, wherein the information diagram comprises a structure diagram and an assembly diagram, identifying an external image component which can be collected by the SQB weighing sensor, marking the external image component as a component to be modeled, establishing a three-dimensional model of the component to be modeled according to the information diagram, marking the three-dimensional model as a component model, combining the component models according to a combination mode in the information diagram to form the SQB weighing sensor model, and marking the SQB weighing sensor model as the integrity detection model;the integrity testing module is used for carrying out completeness testing on the produced SQB weighing sensor, establishing an information acquisition model, carrying out information acquisition on the SQB weighing sensor through the information acquisition model to obtain an acquired image set, establishing an image recognition model, extracting modeling data in the acquired image set through the image recognition model, establishing the modeling model, inputting the modeling data into the modeling model, and obtaining a corresponding acquisition model; acquiring an integrity detection model, comparing the integrity detection model with an acquisition model, and acquiring abnormal parts in the acquisition model; the corresponding SQB load cell is marked as an abnormal SQB load cell.
- 2. The SQB weighing sensor automatic test system of claim 1, wherein the method for establishing the information acquisition model comprises:the method comprises the steps of matching an information acquisition scheme of the SQB weighing sensor, setting an information acquisition device according to the matched information acquisition scheme, identifying a data acquisition flow in the information acquisition scheme, establishing an information acquisition device control model according to the identified data acquisition flow, and integrating the information acquisition device and the information acquisition device control model into the information acquisition model.
- 3. The SQB load cell automatic test system of claim 2, wherein the method of matching an information acquisition scheme of an SQB load cell comprises:obtaining the model and the type of a weighing sensor, compiling an acquisition scheme according to the model and the type of the weighing sensor, establishing a database, storing the acquisition scheme into the database, marking the current database as an acquisition scheme library, obtaining the model of an SQB weighing sensor produced on a current production line, marking the model as a detection model, inputting the detection model into the acquisition scheme library for matching, and obtaining a corresponding information acquisition scheme.
- 4. The SQB weighing sensor automatic testing system of claim 1, wherein the method for comparing the integrity detection model with the collection model to obtain abnormal components in the collection model comprises:and obtaining the similarity between the integrity detection model and the acquisition model, marking as integral similarity, not operating when the integral similarity is not less than a threshold value X1, calculating the similarity between the integrity detection model and a corresponding component model in the acquisition model when the integral similarity is less than a threshold value X1, marking as component similarity, and marking the component model with the component similarity less than a threshold value X2 as an abnormal component.
- 5. The automatic test system of claim 1, further comprising a classification module for classifying abnormal SQB load cells.
- 6. The SQB load cell automatic testing system of claim 5, wherein an assignment library is further established in the modeling module, assignments are made to component models in the SQB load cell model, corresponding assignments are associated to corresponding component models as assignment tags, and the current SQB load cell model is labeled as an integrity detection model.
- 7. The SQB load cell automatic test system of claim 6, wherein the method for assigning values to component models in the SQB load cell model comprises:and acquiring the quantity of the component models needing assignment, selecting series numerical value assignment of corresponding kinds of quantity from an assignment library according to the acquired quantity of the component models, and corresponding representative assignment in the matched series numerical value assignment to the component models to finish assignment of the component models.
- 8. The SQB weighing sensor automatic testing system of claim 7, wherein the working method of the classification module comprises the following steps:acquiring an abnormal component assignment tag corresponding to the abnormal SQB weighing sensor, acquiring component similarity corresponding to the abnormal component, identifying a distinguishing position in the abnormal component according to the component similarity, and performing serial assignment on the abnormal component according to the distinguishing position and the abnormal component assignment tag, wherein the serial assignment is marked as abnormal assignment;acquiring a historical abnormal assignment set, vectorizing the historical abnormal assignment set, marking the vectorized historical abnormal assignment set as a historical assignment vector, mapping the historical assignment vector into a vector space, clustering the historical assignment vector in the vector space through a clustering algorithm to obtain a plurality of clusters, and setting a corresponding cluster label for each cluster;vectorizing the obtained abnormal assignment, marking the abnormal assignment as a detection vector, mapping the detection vector to a vector space for clustering, obtaining a cluster corresponding to the detection vector, obtaining a cluster label corresponding to the cluster, marking the corresponding abnormal component with the corresponding cluster label, and sending the abnormal component to a corresponding storage position according to the distance label.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111671329.7A CN114353925B (en) | 2021-12-31 | 2021-12-31 | Automatic testing system for SQB weighing sensor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111671329.7A CN114353925B (en) | 2021-12-31 | 2021-12-31 | Automatic testing system for SQB weighing sensor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN114353925A true CN114353925A (en) | 2022-04-15 |
| CN114353925B CN114353925B (en) | 2024-04-12 |
Family
ID=81105426
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111671329.7A Active CN114353925B (en) | 2021-12-31 | 2021-12-31 | Automatic testing system for SQB weighing sensor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114353925B (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020066602A1 (en) * | 2000-12-01 | 2002-06-06 | Doug Bliss | Load cell diagnostics and failure prediction weighing apparatus and process |
| CN107491004A (en) * | 2017-08-09 | 2017-12-19 | 北京特种机械研究所 | Intelligent weighing tester and its application method |
| CN109709823A (en) * | 2018-12-26 | 2019-05-03 | 中国北方车辆研究所 | Information integration test method based on model |
| CN110319914A (en) * | 2019-06-06 | 2019-10-11 | 吉旗（成都）科技有限公司 | The fault detection method and device of vehicle load detection device |
| CN111307264A (en) * | 2019-12-30 | 2020-06-19 | 中山佳维电子有限公司 | Scale body testing method and device, storage medium and upper computer |
| CN111624229A (en) * | 2020-05-15 | 2020-09-04 | 嘉兴恒创电力设计研究院有限公司明绘分公司 | Intelligent charged equipment fault diagnosis method based on infrared imaging |
| CN111832647A (en) * | 2020-07-10 | 2020-10-27 | 上海交通大学 | Abnormal flow detection system and method |
| CN111985558A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Electric energy meter abnormity diagnosis method and system |
| CN113762427A (en) * | 2021-11-10 | 2021-12-07 | 聚时科技(江苏)有限公司 | Feeding abnormity detection method in industrial automation detection scene |
-
2021
- 2021-12-31 CN CN202111671329.7A patent/CN114353925B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020066602A1 (en) * | 2000-12-01 | 2002-06-06 | Doug Bliss | Load cell diagnostics and failure prediction weighing apparatus and process |
| CN107491004A (en) * | 2017-08-09 | 2017-12-19 | 北京特种机械研究所 | Intelligent weighing tester and its application method |
| CN109709823A (en) * | 2018-12-26 | 2019-05-03 | 中国北方车辆研究所 | Information integration test method based on model |
| CN110319914A (en) * | 2019-06-06 | 2019-10-11 | 吉旗（成都）科技有限公司 | The fault detection method and device of vehicle load detection device |
| CN111307264A (en) * | 2019-12-30 | 2020-06-19 | 中山佳维电子有限公司 | Scale body testing method and device, storage medium and upper computer |
| CN111624229A (en) * | 2020-05-15 | 2020-09-04 | 嘉兴恒创电力设计研究院有限公司明绘分公司 | Intelligent charged equipment fault diagnosis method based on infrared imaging |
| CN111832647A (en) * | 2020-07-10 | 2020-10-27 | 上海交通大学 | Abnormal flow detection system and method |
| CN111985558A (en) * | 2020-08-19 | 2020-11-24 | 安徽蓝杰鑫信息科技有限公司 | Electric energy meter abnormity diagnosis method and system |
| CN113762427A (en) * | 2021-11-10 | 2021-12-07 | 聚时科技(江苏)有限公司 | Feeding abnormity detection method in industrial automation detection scene |
Also Published As
| Publication number | Publication date |
|---|---|
| CN114353925B (en) | 2024-04-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110598736B (en) | Power equipment infrared image fault positioning, identifying and predicting method | |
| CN112699913A (en) | Transformer area household variable relation abnormity diagnosis method and device | |
| CN109614488B (en) | Text classification and image recognition-based distribution network live working condition judgment method | |
| CN108985380B (en) | Point switch fault identification method based on cluster integration | |
| CN109359697A (en) | Graph image recognition methods and inspection system used in a kind of power equipment inspection | |
| CN103699698A (en) | Method and system for track traffic failure recognition based on improved Bayesian algorithm | |
| CN111145042A (en) | Power distribution network voltage abnormity diagnosis method adopting full-connection neural network | |
| CN104636751A (en) | Crowd abnormity detection and positioning system and method based on time recurrent neural network | |
| CN102522709B (en) | Decision-making method and decision-making system for state overhaul of transformers | |
| CN106482967A (en) | A kind of Cost Sensitive Support Vector Machines locomotive wheel detecting system and method | |
| CN106777622A (en) | The method and system of the electromechanical equipment on-line fault diagnosis based on artificial intelligence | |
| CN114676742A (en) | Power grid abnormal electricity utilization detection method based on attention mechanism and residual error network | |
| CN111126820A (en) | Electricity stealing prevention method and system | |
| CN108416373A (en) | A kind of unbalanced data categorizing system based on regularization Fisher threshold value selection strategies | |
| CN110379036A (en) | Intelligent substation patrol recognition methods, system, device and storage medium | |
| CN113935413A (en) | Distribution network wave recording file waveform identification method based on convolutional neural network | |
| CN112508278A (en) | Multi-connected system load prediction method based on evidence regression multi-model | |
| CN115683504B (en) | Bridge acceleration monitoring data anomaly identification method and system based on multi-label classification | |
| CN114353925B (en) | Automatic testing system for SQB weighing sensor | |
| CN110045691A (en) | A kind of multitasking fault monitoring method of multi-source heterogeneous big data | |
| CN114897193A (en) | Airplane structure maintenance decision method and decision system based on man-in-the-loop | |
| CN114066239A (en) | User power consumption abnormity detection method and device | |
| CN115598459A (en) | Power failure prediction method for 10kV feeder line fault of power distribution network | |
| CN113435494A (en) | Low-voltage resident user abnormal electricity utilization identification method and simulation system | |
| CN207516464U (en) | A kind of Portable metering automatization terminal trouble-shooter |
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 |