CN115526215A - Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault - Google Patents
Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault Download PDFInfo
- Publication number
- CN115526215A CN115526215A CN202211480528.4A CN202211480528A CN115526215A CN 115526215 A CN115526215 A CN 115526215A CN 202211480528 A CN202211480528 A CN 202211480528A CN 115526215 A CN115526215 A CN 115526215A
- Authority
- CN
- China
- Prior art keywords
- determining
- glue pump
- fault
- load
- neural network
- 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
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
- F04B51/00—Testing machines, pumps, or pumping installations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- Y02P90/30—Computing systems specially adapted for manufacturing
Abstract
The invention relates to the technical field of operation monitoring of a glue pump, and particularly discloses a method and a system for diagnosing, maintaining, analyzing and optimizing a glue pump fault, wherein the method comprises the steps of obtaining a design model of the glue pump, carrying out load analysis on the design model, determining a high-risk point position, and arranging a sensor based on the high-risk point position; acquiring sensor data, and determining a glue pump operation table according to the sensor data; the rubber pump operation table comprises a high-risk point location item and a scoring item; determining a fault type based on a rubber pump operation table, and training a neural network model according to the rubber pump operation table and the fault type thereof; and calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model. According to the method, more accurate fault point positions and types can be predicted quickly according to the neural network model, the troubleshooting difficulty is greatly reduced, and the maintenance efficiency is improved.
Description
Technical Field
The invention relates to the technical field of operation monitoring of a rubber pump, in particular to a method and a system for diagnosing, maintaining, analyzing and optimizing a rubber pump fault.
Background
The glue pump is one of pumps, and the glue pump has many classifications, and a large-sized glue pump is mainly used in industrial buildings, and is usually used for slurry residue, and a light glue pump is also provided.
Generally speaking, the function of the glue pump is to extract fluid, the extracted fluid contains a lot of impurities, and the impurities easily damage the glue pump, so that the damage probability of the glue pump is extremely high, the glue pump belongs to easily damaged equipment, a worker needs to repair the glue pump frequently, the worker needs to check the glue pump comprehensively each time, and when the number of the glue pumps is large, the working pressure of the worker is extremely high. How to quickly locate the fault position and the fault type thereof is a technical problem to be solved by the technical scheme of the invention.
Disclosure of Invention
The invention aims to provide a method and a system for diagnosing, maintaining, analyzing and optimizing the fault of a rubber pump, so as to solve the problems in the background technology.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for diagnosing, maintaining, analyzing and optimizing a rubber pump fault comprises the following steps:
acquiring a design model of the rubber pump, carrying out load analysis on the design model, determining a high-risk point position, and arranging a sensor based on the high-risk point position;
receiving a glue pump application scene input by a user, determining a predicted load according to the glue pump application scene, and activating the sensor according to the predicted load; the glue pump application scenario comprises fluid parameters and environmental parameters;
acquiring sensor data, and determining a glue pump operation table according to the sensor data; the rubber pump operation table comprises a high-risk point location item and a scoring item;
determining a fault type based on a rubber pump operation table, and training a neural network model according to the rubber pump operation table and the fault type thereof; the input of the neural network model is a glue pump application scene, and the output is a fault type;
and calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model.
As a further scheme of the invention: the design model of obtaining the glue pump is right the design model carries out load analysis, confirms the high-risk position, and the step based on high-risk position sets up the sensor includes:
acquiring a design model of the glue pump, and determining a connection point position according to the number information in the design model; the data structure of the number information is a tree;
filling virtual fluids with different parameters into the design model, and calculating the virtual load of each connection point according to the virtual fluids;
acquiring deformation parameters at the connecting point positions, and determining high-risk point positions according to the deformation parameters;
and determining the position and the type of the sensor based on the high-risk point location.
As a further scheme of the invention: the step of receiving a glue pump application scenario input by a user, determining a predicted load according to the glue pump application scenario, and activating the sensor according to the predicted load comprises the steps of:
receiving fluid viscosity, a particulate matter mean value, a particulate matter maximum value and a working position input by a user;
acquiring air temperature and air humidity based on the working position;
inputting the fluid viscosity, the particulate matter average value, the particulate matter maximum value, the air temperature and the air humidity into a preset load judgment model to obtain a predicted load; the predicted load comprises a load amount and a load position;
determining a point location center according to the load position, determining a point location radius according to the load amount, and inquiring and activating a target sensor according to the point location center and the point location radius; the point location center is a subset of high-risk point locations.
As a further scheme of the invention: the step of acquiring sensor data and determining the operation table of the glue pump according to the sensor data comprises the following steps:
acquiring sensor data, and converting the sensor data into discrete point groups based on time;
fitting the discrete point group according to a preset fitting model to obtain a data curve and a function of the sensor;
calculating a data curve and a multi-order derivative of a function thereof, acquiring multi-order characteristics, and comparing the multi-order characteristics with preset reference characteristics to obtain scores;
and obtaining the scores of the sensors corresponding to the high-risk point positions, and generating a rubber pump operation table.
As a further scheme of the invention: the method for determining the fault type based on the rubber pump operation table comprises the following steps of:
converting the glue pump operation table into a glue pump operation matrix;
sequentially reading fault characteristics in a preset fault characteristic table, performing traversal matching in a glue pump running matrix based on the fault characteristics, and judging the fault type of the glue pump running table according to the traversal matching result; the fault characteristics are preset matrixes;
reading a glue pump application scene input by a user, building a training set according to the glue pump application scene and the fault type, and training a neural network model;
the process of traversing and matching in the glue pump operation matrix based on the fault characteristics comprises the following steps:
and determining a sliding window based on the fault characteristics, intercepting a sub-matrix in the operation matrix of the glue pump according to the sliding window, calculating a convolution value of the fault characteristics and the sub-matrix, and taking the convolution value as a traversal matching result.
As a further scheme of the invention: the step of calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model comprises the following steps:
when a glue pump application scene is received, inputting a trained neural network model to obtain a first fault type;
determining a second fault type based on a glue pump operating table generated from the sensor data;
calculating an accuracy rate of the first fault type based on the second fault type;
and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model.
The technical scheme of the invention also provides a system for diagnosing, maintaining, analyzing and optimizing the faults of the rubber pump, which comprises the following steps:
the sensor setting module is used for acquiring a design model of the rubber pump, carrying out load analysis on the design model, determining high-risk point positions and setting sensors based on the high-risk point positions;
the sensor activation module is used for receiving a glue pump application scene input by a user, determining a predicted load according to the glue pump application scene, and activating the sensor according to the predicted load; the glue pump application scenario comprises fluid parameters and environmental parameters;
the operation table determining module is used for acquiring sensor data and determining a glue pump operation table according to the sensor data; the rubber pump operation table comprises a high-risk point location item and a scoring item;
the model training module is used for determining the fault type based on the rubber pump operation table and training the neural network model according to the rubber pump operation table and the fault type thereof; the input of the neural network model is a glue pump application scene, and the output is a fault type;
and the model application module is used for calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, the application priority of the neural network model is improved.
As a further scheme of the invention: the sensor setting module includes:
the connection point location determining unit is used for acquiring a design model of the glue pump and determining the connection point location according to the number information in the design model; the data structure of the number information is a tree;
the virtual load calculation unit is used for filling virtual fluids with different parameters into the design model and calculating the virtual load of each connection point according to the virtual fluids;
the high-risk point location selection unit is used for acquiring deformation parameters at the connecting point locations and determining the high-risk point locations according to the deformation parameters;
and the processing execution unit is used for determining the position and the type of the sensor based on the high-risk point location.
As a further scheme of the invention: the sensor activation module includes:
the data receiving unit is used for receiving the fluid viscosity, the particulate mean value, the particulate maximum value and the working position input by a user;
an environmental information acquisition unit for acquiring an air temperature and an air humidity based on the working position;
the load prediction unit is used for inputting the fluid viscosity, the particulate matter average value, the particulate matter maximum value, the air temperature and the air humidity into a preset load judgment model to obtain a predicted load; the predicted load comprises a load amount and a load position;
the query activation unit is used for determining a point location center according to the load position, determining a point location radius according to the load amount, querying a target sensor according to the point location center and the point location radius and activating the target sensor; the point location center is a subset of high-risk point locations.
As a further scheme of the invention: the operation table determining module comprises:
a point group conversion unit for acquiring sensor data and converting the sensor data into a discrete point group based on time;
the point group fitting unit is used for fitting a discrete point group according to a preset fitting model to obtain a data curve and a function of the sensor;
the score generation unit is used for calculating a data curve and a multi-order derivative of a function thereof, acquiring multi-order characteristics, and comparing the multi-order characteristics with preset reference characteristics to obtain a score;
and the data statistical unit is used for acquiring the scores of the sensors corresponding to the high-risk point positions and generating a rubber pump operation table.
Compared with the prior art, the invention has the beneficial effects that: the method is characterized in that high-risk point positions are determined based on a design model of the rubber pump, sensors are installed, working data are collected by the sensors, and fault point positions and types are judged; meanwhile, the application scene is used as input, the fault point location and the type are used as output to train the neural network model, once the glue pump cannot work, the more accurate fault point location and type can be predicted quickly according to the neural network model, the troubleshooting difficulty is greatly reduced, and the maintenance efficiency is improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings used in the embodiments or the description of 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.
Fig. 1 is a flow chart of a method for diagnosing, maintaining, analyzing and optimizing a failure of a glue pump.
Fig. 2 is a first sub-flow block diagram of a method for diagnosing, maintaining, analyzing and optimizing the failure of the glue pump.
Fig. 3 is a second sub-flow block diagram of the method for diagnosing, maintaining, analyzing and optimizing the failure of the glue pump.
Fig. 4 is a third sub-flow block diagram of the method for diagnosing, maintaining, analyzing and optimizing the failure of the glue pump.
Fig. 5 is a fourth sub-flow block diagram of the method for diagnosing, maintaining, analyzing and optimizing the failure of the glue pump.
Fig. 6 is a fifth sub-flow block diagram of the method for diagnosing, maintaining, analyzing and optimizing the failure of the glue pump.
Fig. 7 is a block diagram of the component structure of the system for diagnosing, maintaining, analyzing and optimizing the failure of the glue pump.
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects of the present invention more clearly understood, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
Fig. 1 is a flow chart of a method for diagnosing, maintaining, analyzing, and optimizing a fault of a rubber pump, in an embodiment of the present invention, the method includes:
step S100: acquiring a design model of a rubber pump, carrying out load analysis on the design model, determining a high-risk point position, and setting a sensor based on the high-risk point position;
the design model of the rubber pump is generated in the design stage, belongs to existing data, load analysis is carried out on the design model, different high-risk point positions can be determined, and the sensor is arranged at or near the high-risk point positions.
Step S200: receiving a glue pump application scene input by a user, determining a predicted load according to the glue pump application scene, and activating the sensor according to the predicted load; the glue pump application scenario comprises fluid parameters and environmental parameters;
inputting a glue pump application scene by a user, wherein the glue pump application scene is a parameter of a fluid to be processed and an environmental parameter, and the two factors are matched to influence the use process of the glue pump; the predicted load situation can be determined by the glue pump application scenario, and the preset sensor is activated by the predicted load situation.
Step S300: acquiring sensor data, and determining a rubber pump operation table according to the sensor data; the rubber pump operation table comprises a high-risk point location item and a scoring item;
the activated sensor collects data, and a glue pump operation table is determined according to the collected data, wherein the glue pump operation table reflects the working condition of each high-risk point position.
Step S400: determining a fault type based on a rubber pump operation table, and training a neural network model according to the rubber pump operation table and the fault type thereof; the input of the neural network model is a glue pump application scene, and the output is a fault type;
the glue pump operation table reflects the working condition of each high-risk point location, the working condition of each high-risk point location is analyzed, the fault type can be easily determined, the fault type is used as output, a preset neural network model is trained, and the identification process of the neural network model is more and more accurate along with the increase of the number of samples.
Step S500: calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model;
the recognition accuracy of the neural network model is calculated at regular time, and when the accuracy is high enough, step S300 becomes an optional step, and the neural network model is taken as a main recognition process.
It should be noted that, in practical application, a problem occurs in one glue pump, and what kind of problem occurs in the subsequent manual repair process is clear at a glance, and if the fault type determined by the glue pump operation table is not in accordance with the reality, the operation process of the glue pump operation table needs to be adjusted.
Fig. 2 is a first sub-flow block diagram of a method for diagnosing, maintaining, analyzing, and optimizing a failure of a glue pump, where the method includes the steps of obtaining a design model of the glue pump, performing load analysis on the design model, and determining a high-risk point location, where the step of setting a sensor based on the high-risk point location includes:
step S101: acquiring a design model of the glue pump, and determining a connection point position according to the number information in the design model; the data structure of the number information is a tree;
the glue pump is composed of a plurality of components, and each component is composed of a small component or a small component group, so that the design model is of a tree-shaped structure; the sub-components belonging to the same component have a connection relationship, and the connection point position is a point position which is easy to damage in the glue pump.
Step S102: filling virtual fluids with different parameters into the design model, and calculating the virtual load of each connection point according to the virtual fluids;
filling virtual fluid with different parameters into the design model can be completed in the existing simulation software, and actually, a technical scheme that a worker directly calculates virtual load based on a fluid mechanics formula is feasible is also provided.
Step S103: acquiring deformation parameters at the connecting point positions, and determining high-risk point positions according to the deformation parameters;
and continuously increasing the load, and acquiring deformation parameters of each connection point, wherein the more the deformation parameters are, the higher the vulnerability of the connection point is, so that the connection point is marked as a high-risk point.
Step S104: and determining the position and the type of the sensor based on the high-risk point location.
Arranging a sensor at or near the high-risk point; the process of setting the sensor mainly comprises the step of determining the position and the type of the sensor, which is decided by a worker, and the technical scheme of the invention is not limited.
Fig. 3 is a second sub-flow block diagram of the method for diagnosing, maintaining, analyzing, and optimizing a failure of a glue pump, where the method receives a glue pump application scenario input by a user, determines a predicted load according to the glue pump application scenario, and the step of activating the sensor according to the predicted load includes:
step S201: receiving the fluid viscosity, the particulate matter mean value, the particulate matter maximum value and the working position input by a user;
the fluid viscosity, the particulate mean value and the particulate maximum value are measured by a worker; wherein the maximum value of the particles is a theoretical value; the maximum and mean parameters are sufficient to reflect the particle distribution of the fluid to be treated.
Step S202: acquiring air temperature and air humidity based on the working position;
the air temperature and the air temperature are taken from the working location, both of which may have an effect on certain parts in the glue pump.
Step S203: inputting the fluid viscosity, the particulate matter mean value, the particulate matter maximum value, the air temperature and the air humidity into a preset load judgment model to obtain a predicted load; the predicted load comprises a load amount and a load position;
the data are counted, a preset load judgment model is input, and a predicted load can be obtained; the predicted load includes an applied point and an applied amount.
Step S204: determining a point location center according to the load position, determining a point location radius according to the load amount, and inquiring and activating a target sensor according to the point location center and the point location radius; the point location center is a subset of high-risk point locations;
and inquiring a high-risk point location at the load position to serve as a point location center, and inquiring and activating a set sensor based on the point location center.
Fig. 4 is a third sub-flow block diagram of the method for diagnosing, maintaining, analyzing, and optimizing the failure of the glue pump, where the step of acquiring the sensor data and determining the operation table of the glue pump according to the sensor data includes:
step S301: acquiring sensor data, and converting the sensor data into discrete point groups based on time;
the acquired sensor data are discrete data, and the discrete data are inserted into the same coordinate axis based on time.
Step S302: fitting a discrete point group according to a preset fitting model to obtain a data curve and a function of the sensor;
and fitting the discrete point group to obtain a data curve and a function of the sensor.
Step S303: calculating a data curve and a multi-order derivative of a function thereof, acquiring a multi-order characteristic, and comparing the multi-order characteristic with a preset reference characteristic to obtain a score;
calculating the derivative for multiple times, and continuously acquiring the change characteristics so as to obtain multi-order characteristics; the multi-step features are compared to preset reference features (pre-query statistics) to generate a score for the sensor.
Step S304: obtaining scores of sensors corresponding to the high-risk point positions, and generating a rubber pump operation table;
one sensor may correspond to a plurality of high-risk point positions, the scores of the related sensors are searched by taking the high-risk point positions as the reference, and a rubber pump operation table can be generated.
Fig. 5 is a fourth sub-flow block diagram of the method for diagnosing, maintaining, analyzing, and optimizing the failure of the glue pump, wherein the step of determining the failure type based on the glue pump operation table and training the neural network model according to the glue pump operation table and the failure type thereof includes:
step S401: converting the rubber pump operation table into a rubber pump operation matrix;
respectively comparing sub-characteristics corresponding to each order of derivative in the multi-order characteristics, wherein the generated scoring items in the rubber pump operation table are a plurality of scores; whether a single score or multiple scores, the glue pump operation table may be converted to a glue pump operation matrix.
Step S402: sequentially reading fault characteristics in a preset fault characteristic table, performing traversal matching in a glue pump running matrix based on the fault characteristics, and judging the fault type of the glue pump running table according to the traversal matching result; the fault characteristics are preset matrixes;
whether an area matched with the fault characteristics exists in the glue pump operation matrix can be judged by sliding the preset fault characteristics in the glue pump operation matrix and calculating convolution, if yes, the existence of the fault is indicated, and the fault type corresponding to the fault characteristics can be inquired.
The process of traversing and matching in the glue pump operation matrix based on the fault characteristics is as follows:
and determining a sliding window based on the fault characteristics, intercepting a sub-matrix in the operation matrix of the glue pump according to the sliding window, calculating a convolution value of the fault characteristics and the sub-matrix, and taking the convolution value as a traversal matching result.
Step S403: reading a glue pump application scene input by a user, building a training set according to the glue pump application scene and the fault type, and training a neural network model;
and constructing a training set by input and output, and training the self-recognition model.
Fig. 6 is a fifth sub-flow block diagram of the method for diagnosing, maintaining, analyzing, and optimizing the failure of the rubber pump, wherein the step of periodically calculating the accuracy of the neural network model, and when the accuracy reaches a preset threshold, the step of increasing the application priority of the neural network model includes:
step S501: when a glue pump application scene is received, inputting a trained neural network model to obtain a first fault type;
step S502: determining a second fault type based on a glue pump operation table generated by the sensor data;
step S503: calculating an accuracy rate of the first fault type based on the second fault type;
and comparing the recognition result of the neural network model with the recognition result of the rubber pump operation table, and judging the recognition accuracy of the neural network model by taking the recognition result of the rubber pump operation table as a reference. It should be noted that the problem found in the actual maintenance process is the most accurate problem, and if the identification result of the glue pump operation table is different from the problem found in the actual maintenance process, the identification process of the glue pump operation table needs to be adjusted.
Step S504: when the accuracy reaches a preset threshold value, improving the application priority of the neural network model;
when the accuracy is high enough, the neural network model serves as the main recognition means.
Example 2
Fig. 7 is a block diagram of a composition structure of a system for diagnosing, maintaining, analyzing, and optimizing a failure of a rubber pump, in an embodiment of the present invention, where the system 10 includes:
the sensor setting module 11 is used for acquiring a design model of the rubber pump, performing load analysis on the design model, determining high-risk point positions, and setting sensors based on the high-risk point positions;
the sensor activation module 12 is configured to receive a glue pump application scenario input by a user, determine a predicted load according to the glue pump application scenario, and activate the sensor according to the predicted load; the glue pump application scenario comprises fluid parameters and environmental parameters;
the operation table determining module 13 is used for acquiring sensor data and determining a rubber pump operation table according to the sensor data; the rubber pump operation table comprises a high-risk point location item and a scoring item;
the model training module 14 is used for determining the fault type based on the rubber pump operation table and training a neural network model according to the rubber pump operation table and the fault type thereof; the input of the neural network model is a glue pump application scene, and the output is a fault type;
and the model application module 15 is used for calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model.
The sensor setting module 11 includes:
the connection point position determining unit is used for acquiring a design model of the glue pump and determining connection point positions according to the number information in the design model; the data structure of the number information is a tree;
the virtual load calculation unit is used for filling virtual fluids with different parameters into the design model and calculating the virtual load of each connection point according to the virtual fluids;
the high-risk point location selection unit is used for acquiring deformation parameters at the connecting point locations and determining the high-risk point locations according to the deformation parameters;
and the processing execution unit is used for determining the position and the type of the sensor based on the high-risk point location.
The sensor activation module 12 includes:
the data receiving unit is used for receiving the fluid viscosity, the particulate mean value, the particulate maximum value and the working position input by a user;
an environmental information acquisition unit for acquiring an air temperature and an air humidity based on the working position;
the load prediction unit is used for inputting the fluid viscosity, the particulate matter mean value, the particulate matter maximum value, the air temperature and the air humidity into a preset load judgment model to obtain a predicted load; the predicted load comprises a load amount and a load position;
the query activation unit is used for determining a point location center according to the load position, determining a point location radius according to the load capacity, and querying and activating a target sensor according to the point location center and the point location radius; the point location center is a subset of high-risk point locations.
The operation table determining module 13 includes:
a point group conversion unit for acquiring sensor data, and converting the sensor data into a discrete point group based on time;
the point group fitting unit is used for fitting the discrete point group according to a preset fitting model to obtain a data curve and a function of the sensor;
the score generation unit is used for calculating a data curve and a multi-order derivative of a function of the data curve, acquiring multi-order characteristics, and comparing the multi-order characteristics with preset reference characteristics to obtain a score;
and the data statistical unit is used for acquiring the scores of the sensors corresponding to the high-risk point positions and generating a rubber pump operation table.
The functions which can be realized by the method for analyzing, analyzing and optimizing the fault diagnosis and the maintenance of the glue pump are all completed by computer equipment, and the computer equipment comprises one or more processors and one or more memories, wherein at least one program code is stored in the one or more memories, and the program code is loaded and executed by the one or more processors to realize the functions of the method for analyzing, analyzing and optimizing the fault diagnosis and the maintenance of the glue pump.
The processor fetches instructions and analyzes the instructions one by one from the memory, then completes corresponding operations according to the instruction requirements, generates a series of control commands, enables all parts of the computer to automatically, continuously and coordinately act to form an organic whole, realizes the input of programs, the input of data, the operation and the output of results, and the arithmetic operation or the logic operation generated in the process is completed by the arithmetic unit; the Memory comprises a Read-Only Memory (ROM) for storing a computer program, and a protection device is arranged outside the Memory.
Illustratively, the computer program may be partitioned into one or more modules, stored in memory and executed by a processor, to implement the invention. One or more of the modules may be a series of computer program instruction segments capable of performing certain functions, which are used to describe the execution of the computer program in the terminal device.
Those skilled in the art will appreciate that the above description of the service device is merely exemplary and not limiting of the terminal device, and may include more or less components than those described, or combine certain components, or different components, such as may include input output devices, network access devices, buses, etc.
The Processor may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), an off-the-shelf Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic, discrete hardware components, etc. The general-purpose processor may be a microprocessor or the processor may be any conventional processor or the like, which is the control center of the terminal equipment and connects the various parts of the entire user terminal using various interfaces and lines.
The memory may be used to store computer programs and/or modules, and the processor may implement various functions of the terminal device by operating or executing the computer programs and/or modules stored in the memory and calling data stored in the memory. The memory mainly comprises a storage program area and a storage data area, wherein the storage program area can store an operating system, application programs (such as an information acquisition template display function, a product information publishing function and the like) required by at least one function and the like; the storage data area may store data created according to the use of the berth-state display system (e.g., product information acquisition templates corresponding to different product types, product information that needs to be issued by different product providers, etc.), and the like. In addition, the memory may include high-speed random access memory, and may also include non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), at least one magnetic disk storage device, a Flash memory device, or other volatile solid state storage device.
The terminal device integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the modules/units in the system according to the above embodiment may be implemented by a computer program, which may be stored in a computer-readable storage medium and used by a processor to implement the functions of the embodiments of the system. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, U.S. disk, removable hard disk, magnetic disk, optical disk, computer Memory, read-Only Memory (ROM), random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution media, and the like.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrases "comprising a component of' 8230; \8230;" does not exclude the presence of another like element in a process, method, article, or apparatus that comprises the element.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the scope of the present invention, and all equivalent structures or equivalent processes performed by the present invention or directly or indirectly applied to other related technical fields are also included in the scope of the present invention.
Claims (10)
1. A method for diagnosing, maintaining, analyzing and optimizing a rubber pump fault is characterized by comprising the following steps:
acquiring a design model of the rubber pump, carrying out load analysis on the design model, determining a high-risk point position, and arranging a sensor based on the high-risk point position;
receiving a glue pump application scene input by a user, determining a predicted load according to the glue pump application scene, and activating the sensor according to the predicted load; the glue pump application scenario comprises fluid parameters and environmental parameters;
acquiring sensor data, and determining a glue pump operation table according to the sensor data; the rubber pump operation table comprises a high-risk point location item and a scoring item;
determining a fault type based on a rubber pump operation table, and training a neural network model according to the rubber pump operation table and the fault type thereof; the input of the neural network model is a glue pump application scene, and the output is a fault type;
and calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model.
2. The method for diagnosing, maintaining, analyzing and optimizing the failure of the rubber pump according to claim 1, wherein the step of obtaining a design model of the rubber pump, performing load analysis on the design model, and determining a high-risk point position comprises the steps of:
acquiring a design model of the glue pump, and determining a connection point position according to the number information in the design model; the data structure of the number information is a tree;
filling virtual fluids with different parameters into the design model, and calculating the virtual load of each connection point according to the virtual fluids;
acquiring deformation parameters at the connecting point positions, and determining high-risk point positions according to the deformation parameters;
and determining the position and the type of the sensor based on the high-risk point location.
3. The method for diagnosing, maintaining, analyzing and optimizing the failure of the glue pump according to claim 1, wherein the step of receiving a glue pump application scenario input by a user, determining a predicted load according to the glue pump application scenario, and activating the sensor according to the predicted load comprises:
receiving the fluid viscosity, the particulate matter mean value, the particulate matter maximum value and the working position input by a user;
acquiring air temperature and air humidity based on the working position;
inputting the fluid viscosity, the particulate matter average value, the particulate matter maximum value, the air temperature and the air humidity into a preset load judgment model to obtain a predicted load; the predicted load comprises a load amount and a load position;
determining a point location center according to the load position, determining a point location radius according to the load amount, and inquiring and activating a target sensor according to the point location center and the point location radius; the point location center is a subset of high risk point locations.
4. The method for diagnosing, maintaining, analyzing and optimizing the fault of the glue pump as claimed in claim 1, wherein the step of obtaining the sensor data and determining the operation table of the glue pump according to the sensor data comprises:
acquiring sensor data, and converting the sensor data into discrete point groups based on time;
fitting the discrete point group according to a preset fitting model to obtain a data curve and a function of the sensor;
calculating a data curve and a multi-order derivative of a function thereof, acquiring multi-order characteristics, and comparing the multi-order characteristics with preset reference characteristics to obtain scores;
and obtaining the scores of the sensors corresponding to the high-risk point positions, and generating a rubber pump operation table.
5. The method for diagnosing, maintaining, analyzing and optimizing the faults of the rubber pump according to claim 1, wherein the fault types are determined based on a rubber pump operation table, and the step of training the neural network model according to the rubber pump operation table and the fault types thereof comprises the following steps:
converting the glue pump operation table into a glue pump operation matrix;
sequentially reading fault characteristics in a preset fault characteristic table, performing traversal matching in a glue pump running matrix based on the fault characteristics, and judging the fault type of the glue pump running table according to a traversal matching result; the fault characteristics are preset matrixes;
reading a glue pump application scene input by a user, building a training set according to the glue pump application scene and the fault type, and training a neural network model;
the process of traversing and matching in the operation matrix of the glue pump based on the fault characteristics is as follows:
and determining a sliding window based on the fault characteristics, intercepting a sub-matrix in the operation matrix of the glue pump according to the sliding window, calculating a convolution value of the fault characteristics and the sub-matrix, and taking the convolution value as a traversal matching result.
6. The method for diagnosing, maintaining, analyzing and optimizing the rubber pump fault according to claim 1, wherein the step of periodically calculating the accuracy of the neural network model, and when the accuracy reaches a preset threshold, increasing the application priority of the neural network model comprises the steps of:
when a glue pump application scene is received, inputting a trained neural network model to obtain a first fault type;
determining a second fault type based on a glue pump operating table generated from the sensor data;
calculating an accuracy rate of the first fault type based on the second fault type;
and when the accuracy reaches a preset threshold value, improving the application priority of the neural network model.
7. A system for diagnosing, maintaining, analyzing and optimizing a fault of a rubber pump, which is characterized by comprising:
the sensor setting module is used for acquiring a design model of the rubber pump, carrying out load analysis on the design model, determining high-risk point positions and setting sensors based on the high-risk point positions;
the sensor activation module is used for receiving a glue pump application scene input by a user, determining a predicted load according to the glue pump application scene, and activating the sensor according to the predicted load; the glue pump application scenario comprises fluid parameters and environmental parameters;
the operation table determining module is used for acquiring sensor data and determining a glue pump operation table according to the sensor data; the rubber pump operation table comprises a high-risk point location item and a scoring item;
the model training module is used for determining the fault type based on the rubber pump operation table and training a neural network model according to the rubber pump operation table and the fault type thereof; the input of the neural network model is a glue pump application scene, and the output is a fault type;
and the model application module is used for calculating the accuracy of the neural network model at regular time, and when the accuracy reaches a preset threshold value, the application priority of the neural network model is improved.
8. The system of claim 7, wherein the sensor setting module comprises:
the connection point location determining unit is used for acquiring a design model of the glue pump and determining the connection point location according to the number information in the design model; the data structure of the number information is a tree;
the virtual load calculation unit is used for filling virtual fluids with different parameters into the design model and calculating the virtual load of each connection point according to the virtual fluids;
the high-risk point location selection unit is used for acquiring deformation parameters at the connecting point locations and determining the high-risk point locations according to the deformation parameters;
and the processing execution unit is used for determining the position and the type of the sensor based on the high-risk point location.
9. The system of claim 7, wherein the sensor activation module comprises:
the data receiving unit is used for receiving the fluid viscosity, the particulate matter mean value, the particulate matter maximum value and the working position input by a user;
an environmental information acquisition unit for acquiring an air temperature and an air humidity based on the working position;
the load prediction unit is used for inputting the fluid viscosity, the particulate matter mean value, the particulate matter maximum value, the air temperature and the air humidity into a preset load judgment model to obtain a predicted load; the predicted load comprises a load amount and a load position;
the query activation unit is used for determining a point location center according to the load position, determining a point location radius according to the load amount, querying a target sensor according to the point location center and the point location radius and activating the target sensor; the point location center is a subset of high-risk point locations.
10. The system of claim 7, wherein the operational table determination module comprises:
a point group conversion unit for acquiring sensor data, and converting the sensor data into a discrete point group based on time;
the point group fitting unit is used for fitting the discrete point group according to a preset fitting model to obtain a data curve and a function of the sensor;
the score generation unit is used for calculating a data curve and a multi-order derivative of a function thereof, acquiring multi-order characteristics, and comparing the multi-order characteristics with preset reference characteristics to obtain a score;
and the data statistical unit is used for acquiring the scores of the sensors corresponding to the high-risk point positions and generating a rubber pump operation table.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211480528.4A CN115526215B (en) | 2022-11-24 | 2022-11-24 | Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211480528.4A CN115526215B (en) | 2022-11-24 | 2022-11-24 | Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115526215A true CN115526215A (en) | 2022-12-27 |
| CN115526215B CN115526215B (en) | 2023-04-07 |
Family
ID=84704955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211480528.4A Active CN115526215B (en) | 2022-11-24 | 2022-11-24 | Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115526215B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117289685A (en) * | 2023-11-27 | 2023-12-26 | 青岛创新奇智科技集团股份有限公司 | Production line fault prediction and self-healing method and system based on artificial intelligence |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000064964A (en) * | 1998-08-21 | 2000-03-03 | Ebara Corp | Failure prediction system of vacuum pump |
| CN211343308U (en) * | 2019-11-22 | 2020-08-25 | 武汉德宝装备股份有限公司 | Rubber coating pump operation condition monitored control system |
| CN113418640A (en) * | 2021-05-07 | 2021-09-21 | 武汉理工大学 | Polar region ship anchor windlass roller stress detection device and stress detection method |
| CN113627461A (en) * | 2021-06-21 | 2021-11-09 | 江苏省镔鑫钢铁集团有限公司 | Belt conveyor fault diagnosis method, device and equipment based on PSO-BP algorithm |
| CN113762486A (en) * | 2021-11-11 | 2021-12-07 | 中国南方电网有限责任公司超高压输电公司广州局 | Method and device for constructing fault diagnosis model of converter valve and computer equipment |
| CN114065636A (en) * | 2021-11-23 | 2022-02-18 | 江苏科技大学 | Marine winch brake mechanism fault diagnosis method based on data driving |
| WO2022067562A1 (en) * | 2020-09-29 | 2022-04-07 | 西门子股份公司 | Method and device for diagnosing fault arc, and computer-readable storage medium |
| CN114414935A (en) * | 2021-12-15 | 2022-04-29 | 国网四川省电力公司信息通信公司 | Automatic positioning method and system for feeder fault area of power distribution network based on big data |
| CN115099260A (en) * | 2021-03-05 | 2022-09-23 | 中国石油化工股份有限公司 | Online monitoring mechanical fault real-time diagnosis method for double-screw oil transfer pump |
| CN115270882A (en) * | 2022-08-01 | 2022-11-01 | 上海交通大学 | Light-weight intelligent fault diagnosis method and system based on neural ordinary differential equation |
-
2022
- 2022-11-24 CN CN202211480528.4A patent/CN115526215B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2000064964A (en) * | 1998-08-21 | 2000-03-03 | Ebara Corp | Failure prediction system of vacuum pump |
| CN211343308U (en) * | 2019-11-22 | 2020-08-25 | 武汉德宝装备股份有限公司 | Rubber coating pump operation condition monitored control system |
| WO2022067562A1 (en) * | 2020-09-29 | 2022-04-07 | 西门子股份公司 | Method and device for diagnosing fault arc, and computer-readable storage medium |
| CN115099260A (en) * | 2021-03-05 | 2022-09-23 | 中国石油化工股份有限公司 | Online monitoring mechanical fault real-time diagnosis method for double-screw oil transfer pump |
| CN113418640A (en) * | 2021-05-07 | 2021-09-21 | 武汉理工大学 | Polar region ship anchor windlass roller stress detection device and stress detection method |
| CN113627461A (en) * | 2021-06-21 | 2021-11-09 | 江苏省镔鑫钢铁集团有限公司 | Belt conveyor fault diagnosis method, device and equipment based on PSO-BP algorithm |
| CN113762486A (en) * | 2021-11-11 | 2021-12-07 | 中国南方电网有限责任公司超高压输电公司广州局 | Method and device for constructing fault diagnosis model of converter valve and computer equipment |
| CN114065636A (en) * | 2021-11-23 | 2022-02-18 | 江苏科技大学 | Marine winch brake mechanism fault diagnosis method based on data driving |
| CN114414935A (en) * | 2021-12-15 | 2022-04-29 | 国网四川省电力公司信息通信公司 | Automatic positioning method and system for feeder fault area of power distribution network based on big data |
| CN115270882A (en) * | 2022-08-01 | 2022-11-01 | 上海交通大学 | Light-weight intelligent fault diagnosis method and system based on neural ordinary differential equation |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117289685A (en) * | 2023-11-27 | 2023-12-26 | 青岛创新奇智科技集团股份有限公司 | Production line fault prediction and self-healing method and system based on artificial intelligence |
| CN117289685B (en) * | 2023-11-27 | 2024-02-02 | 青岛创新奇智科技集团股份有限公司 | Production line fault prediction and self-healing method and system based on artificial intelligence |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115526215B (en) | 2023-04-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112383891B (en) | Equipment registration method and device based on object model automatic matching | |
| WO2020062702A9 (en) | Method and device for sending text messages, computer device and storage medium | |
| CN115526215B (en) | Method and system for diagnosing, maintaining, analyzing and optimizing rubber pump fault | |
| CN103366091B (en) | Based on the abnormal tax return data detection method of multilevel threshold exponent-weighted average | |
| CN114414935A (en) | Automatic positioning method and system for feeder fault area of power distribution network based on big data | |
| CN113393211B (en) | Method and system for intelligently improving automatic production efficiency | |
| US20140019215A1 (en) | System for assessing procedure compliance level of human operators in nuclear power plants and method thereof | |
| CN116876950B (en) | Intelligent door and window control system and method, computer equipment and storage medium | |
| CN115330887B (en) | Automatic test system and test method for intelligent substation protection device | |
| CN111695730A (en) | ARIMA and RNN-based vertical mill vibration prediction method and device | |
| CN116596441A (en) | Intelligent warehouse service management method and system based on cloud computing | |
| CN116416884A (en) | Testing device and testing method for display module | |
| CN110543869A (en) | Ball screw service life prediction method and device, computer equipment and storage medium | |
| CN117193088A (en) | Industrial equipment monitoring method and device and server | |
| CN117036947A (en) | Image recognition-based agricultural risk early warning method, device, equipment and medium | |
| CN113020428B (en) | Progressive die machining monitoring method, device, equipment and storage medium | |
| CN115734072A (en) | Internet of things centralized monitoring method and device for industrial automation equipment | |
| CN115484112A (en) | Payment big data security protection method and system and cloud platform | |
| CN115424106A (en) | Trolley detection method and device, electronic equipment and storage medium | |
| CN103914027A (en) | Method for monitoring and managing industrial on-site bottom layer device through expression analysis | |
| CN115526274A (en) | Method, system, equipment and medium for diagnosing faults of sensors in air handling unit | |
| CN113900865B (en) | Intelligent power grid equipment automatic test method, system and readable storage medium | |
| CN114119052B (en) | Big data-based counterfeit agricultural product monitoring method and system | |
| CN113724826B (en) | Method and device for monitoring medical behaviors, computer equipment and storage medium | |
| CN116484230B (en) | Method for identifying abnormal business data and training method of AI digital person |
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 |