CN113085120A - Device and method for online monitoring abrasion state of check valve of injection molding machine - Google Patents
Device and method for online monitoring abrasion state of check valve of injection molding machine Download PDFInfo
- Publication number
- CN113085120A CN113085120A CN202110356075.3A CN202110356075A CN113085120A CN 113085120 A CN113085120 A CN 113085120A CN 202110356075 A CN202110356075 A CN 202110356075A CN 113085120 A CN113085120 A CN 113085120A
- Authority
- CN
- China
- Prior art keywords
- injection molding
- check valve
- screw
- molding machine
- information
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C45/00—Injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould; Apparatus therefor
- B29C45/17—Component parts, details or accessories; Auxiliary operations
- B29C45/76—Measuring, controlling or regulating
- B29C45/768—Detecting defective moulding conditions
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B29—WORKING OF PLASTICS; WORKING OF SUBSTANCES IN A PLASTIC STATE IN GENERAL
- B29C—SHAPING OR JOINING OF PLASTICS; SHAPING OF MATERIAL IN A PLASTIC STATE, NOT OTHERWISE PROVIDED FOR; AFTER-TREATMENT OF THE SHAPED PRODUCTS, e.g. REPAIRING
- B29C2945/00—Indexing scheme relating to injection moulding, i.e. forcing the required volume of moulding material through a nozzle into a closed mould
- B29C2945/76—Measuring, controlling or regulating
- B29C2945/76929—Controlling method
- B29C2945/76973—By counting
Landscapes
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Mechanical Engineering (AREA)
- Injection Moulding Of Plastics Or The Like (AREA)
Abstract
本发明公开了一种在线监测注塑机止逆阀磨损状态的装置与方法，该装置包括直线位移传感器、荷重元压力传感器、注塑机工况采集装置、微处理器、终端设备，微处理器分别与直线位移传感器、荷重元压力传感器、注塑机工况采集装置、终端设备连接，注塑机工况采集装置还与注塑机连接；直线位移传感器用于采集螺杆位移信息，荷重元压力传感器用于采集螺杆受力信息，注塑机工况采集装置用于采集注塑工况信息；微处理器用于根据螺杆位移信息、螺杆受力信息、注塑工况信息确定止逆阀磨损状态；终端设备用于显示止逆阀磨损状态。本发明根据止逆阀的磨损状态，实现对止逆阀的预测性维护，减少检修成本。
The invention discloses a device and a method for online monitoring of the wear state of a check valve of an injection molding machine. The device includes a linear displacement sensor, a load cell pressure sensor, a working condition acquisition device of the injection molding machine, a microprocessor, and terminal equipment. It is connected with linear displacement sensor, load cell pressure sensor, injection molding machine working condition acquisition device, and terminal equipment, and the injection molding machine working condition acquisition device is also connected with the injection molding machine; the linear displacement sensor is used to collect screw displacement information, and the load cell pressure sensor is used to collect The screw force information, the injection molding machine working condition collection device is used to collect the injection molding working condition information; the microprocessor is used to determine the wear state of the check valve according to the screw displacement information, screw force information, and injection molding working condition information; Reverse valve wear condition. According to the wear state of the check valve, the present invention realizes the predictive maintenance of the check valve and reduces the maintenance cost.
Description
Technical Field
The invention relates to the technical field of injection molding machine monitoring, in particular to a device and a method for monitoring the abrasion state of a check valve of an injection molding machine on line.
Background
At present, the injection molding machine is maintained in an actual factory mostly in a preventive maintenance mode, which wastes a great amount of time and maintenance cost. With the development of industrial technology, predictive maintenance technology is gradually developed, which can repair and replace parts in time before a fault occurs, and prevent the equipment from stopping due to the fault. The predictive maintenance technology can gradually develop the injection molding machine into a full-automatic injection molding machine which has the functions of automatically monitoring the use states of all key parts and predicting the residual service life of the key parts.
The check valve is a vulnerable product in the injection molding process and a key part for determining the quality of an injection molded product, so that the check valve needs to be predictively maintained. The screw head of the existing injection molding machine consists of a glue dividing nozzle, a glue plugging ring and a glue injecting meson. The check valve consists of two parts, including a rubber ring and a rubber medium, and has the functions of reverse flow, etc. during injection molding. In the injection molding process, the polymer material contains glass fiber, metal powder, silicate and the like, which cause abrasion failure on the check valve, thereby increasing the rejection rate. The abrasion part of the check valve generally occurs at the matching surface between the inner diameter and the outer diameter of the bolt rubber ring and the glue injection meson, the abrasion of the parts can cause the glue sealing effect to be poor, and even directly cause the backflow of materials during injection, thereby causing the defect of glue shortage of products. The check valve of the injection molding machine belongs to consumables, related stocks are not established in many enterprises, once the check valve fails and cannot be used, shutdown and production halt can be caused, and the production plan of the whole following factory is influenced. It is therefore necessary to monitor the wear state of the non-return valve on-line to achieve predictive maintenance of the non-return valve.
Disclosure of Invention
In order to overcome the defects and shortcomings in the prior art, the invention provides a device for monitoring the abrasion state of a check valve of an injection molding machine on line.
The second purpose of the invention is to provide a method for monitoring the abrasion state of the check valve of the injection molding machine on line.
In order to achieve the purpose, the invention adopts the following technical scheme:
a device for monitoring the abrasion state of a check valve of an injection molding machine on line is provided with a microprocessor, and further comprises a linear displacement sensor, a load cell pressure sensor, an injection molding machine working condition acquisition device and a terminal device, wherein the microprocessor is respectively connected with the linear displacement sensor, the load cell pressure sensor, the injection molding machine working condition acquisition device and the terminal device, and the injection molding machine working condition acquisition device is also connected with the injection molding machine;
the linear displacement sensor, the load cell pressure sensor and the injection molding machine working condition acquisition device are all arranged on the injection molding machine, the linear displacement sensor is used for acquiring screw displacement information, the load cell pressure sensor is used for acquiring screw stress information, and the injection molding machine working condition acquisition device is used for acquiring injection molding working condition information;
the microprocessor is used for forming injection molding input data according to the screw displacement information, the screw stress information and the injection molding working condition information, outputting the abrasion degree of the check valve, setting different levels of abrasion state thresholds and determining the abrasion state of the check valve according to the abrasion degree of the check valve and the different levels of abrasion state thresholds;
the terminal equipment is used for displaying the abrasion state of the check valve.
Preferably, the linear displacement sensor is disposed at a distal end side of the screw.
Preferably, the load cell pressure sensor is provided at a distal end edge portion of the screw.
As the preferred technical scheme, the injection molding machine working condition acquisition device is randomly arranged on the injection molding machine.
As a preferred technical solution, the injection molding condition information specifically includes an injection speed, a minimum padding, a V/P conversion point, and a raw material process condition.
As a preferred technical scheme, the raw material process conditions comprise melt index performance indexes.
In order to achieve the second object, the invention adopts the following technical scheme:
a method for monitoring the abrasion state of a check valve of an injection molding machine on line comprises the following steps:
and (3) acquiring injection molding data: acquiring screw displacement information, screw stress information and injection molding working condition information;
acquiring and processing injection molding data: converting the screw displacement information and the screw stress information from analog signals into digital signals, and performing fitting processing based on the screw displacement information and the screw stress information to form injection molding process data, wherein the injection molding process data comprises a load cell pressure curve and a screw displacement curve;
an injection molding characteristic set generation step: extracting data characteristics based on injection molding process data and performing characteristic vectorization by combining injection molding working condition information to obtain an injection molding characteristic set, wherein the data characteristics comprise a maximum value, a mean value, a covariance, a skewness and power consumption of single injection molding;
predicting the abrasion state of the check valve: and predicting based on the injection molding feature set and a check valve wear state evaluation model after machine learning training, and determining the wear state of the check valve.
As a preferred technical scheme, the training data acquisition step specifically sets the injection molding machine to acquire the training data at the same temperature, the same injection speed and the same material.
As a preferred technical scheme, the injection molding feature set generating step specifically comprises the following steps:
extracting injection molding process data, extracting first data characteristics, forming a first injection molding data characteristic matrix based on the first data characteristics, and performing characteristic vectorization on the first injection molding data characteristic matrix to obtain a first characteristic vector of a single injection molding sample;
and calculating the power consumption of single injection molding by combining a load cell pressure curve and a screw displacement curve and adopting an injection molding power consumption formula, wherein the injection molding power consumption formula specifically comprises the following steps:
w＝∫floadcell(t)·f’position(t)dt
wherein f isloadcell(t) represents a load cell pressure curve function, f'position(t) represents screw speed, w represents screw work of single injection molding, and t represents time variable;
adding the screw work w of single injection molding into the first characteristic vector of the injection molding sample to obtain a second characteristic vector of the injection molding sample, and performing characteristic vectorization by combining the second characteristic vector of the injection molding sample and injection molding condition information to form a third characteristic vector of the injection molding sample;
and integrating the third feature vectors of all injection molding samples into one injection molding feature set.
As a preferable technical solution, in the check valve wear state prediction step, the check valve wear state estimation model after machine learning training is established by using the following steps:
a wear state simulation step: the check valves with different degrees of wear defects are manufactured respectively to simulate the check valves with different degrees of wear states, and the check valves with different wear states are simulated by forming notches with different depths between the bolt rubber ring and the injection rubber medium;
a training data acquisition step: acquiring screw displacement information, screw stress information and injection molding condition information under different wear states of the check valve;
training data acquisition and processing steps: converting the screw displacement information and the screw stress information from analog signals into digital signals, and performing fitting processing based on the screw displacement information and the screw stress information to form injection molding process data, wherein the injection molding process data comprises a load cell pressure curve and a screw displacement curve;
a training set generation step: extracting data characteristics based on the injection molding process data, performing characteristic vectorization by combining injection molding working condition information to obtain an injection molding characteristic set, and forming an injection molding training set by using the abrasion degree of the check valve as a training label;
training: and establishing a check valve wear state evaluation model by using a machine learning algorithm, and finishing training when the preset training times are reached and the test accuracy value of the check valve wear degree reaches a preset test accuracy threshold value, thus obtaining the trained check valve wear state evaluation model.
Compared with the prior art, the invention has the following advantages and beneficial effects:
(1) according to the invention, the load cell pressure sensor and the linear displacement sensor are respectively arranged at the rear part of the screw and the moving end of the screw, so that the on-line monitoring of the abrasion state of the check valve is realized on the premise of not damaging the structure of the injection molding machine; the method has the advantages that the data characteristics of the process data are extracted, the working condition data are combined, the abrasion state evaluation model of the check valve is established based on the algorithm of machine learning, the evaluation model can be well suitable for the injection molding industry with various working condition characteristics, a certain generalization effect is achieved, the abrasion state of the check valve is obtained through monitoring, factories and enterprises are helped to avoid unnecessary periodic detection and maintenance, and a large amount of maintenance cost is reduced.
Drawings
FIG. 1 is a schematic connection diagram of an apparatus for on-line monitoring of a check valve wear state of an injection molding machine in embodiment 1 of the present invention;
FIG. 2 is a schematic structural diagram of an apparatus for online monitoring of a wear state of a check valve of an injection molding machine in embodiment 1 of the present invention;
fig. 3 is a flowchart of a method for online monitoring of the wear state of a check valve of an injection molding machine in embodiment 2 of the invention.
The system comprises an injection molding machine 1, a linear displacement sensor 2, a load cell pressure sensor 3, a microprocessor 4 and a terminal device 5.
Detailed Description
In the description of the present disclosure, it should be noted that the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing and simplifying the present disclosure, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and thus, should not be construed as limiting the present disclosure.
Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. Also, the use of the terms "a," "an," or "the" and similar referents do not denote a limitation of quantity, but rather denote the presence of at least one. The word "comprising" or "comprises", and the like, means that the element or item appearing before the word covers the element or item listed after the word and its equivalents, but does not exclude other elements or items. The terms "connected" or "coupled" and the like are not restricted to physical or mechanical connections, but may include electrical connections, whether direct or indirect.
In the description of the present disclosure, it is to be noted that the terms "mounted," "connected," and "connected" are to be construed broadly unless otherwise explicitly stated or limited. For example, the connection can be fixed, detachable or integrated; can be mechanically or electrically connected; they may be connected directly or indirectly through intervening media, or they may be interconnected between two elements. The specific meaning of the above terms in the present disclosure can be understood in specific instances by those of ordinary skill in the art. In addition, technical features involved in different embodiments of the present disclosure described below may be combined with each other as long as they do not conflict with each other.
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further 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.
Examples
Example 1
As shown in fig. 1 and fig. 2, the present embodiment provides a device for online monitoring of a wear state of a check valve of an injection molding machine, the device includes a linear displacement sensor 2, a load cell pressure sensor 3, an injection molding machine working condition acquisition device, a microprocessor 4, and a terminal device 5, the microprocessor 4 is respectively connected with the linear displacement sensor 2, the load cell pressure sensor 3, the injection molding machine working condition acquisition device, and the terminal device 5, and the injection molding machine working condition acquisition device is further connected with the injection molding machine 1. Wherein the injection molding machine 1 is provided with a screw.
Referring to fig. 1, an injection molding machine operating condition acquisition device is used as a lower computer of an injection molding machine 1, and a linear displacement sensor 2, a load cell pressure sensor 3 and the injection molding machine operating condition acquisition device are all arranged in the injection molding machine 1.
Referring to fig. 1, the linear displacement sensor 2 is disposed at one side of the end of the screw, specifically, one end of the linear displacement sensor 2 is mounted on a fixed support of the injection platform of the injection molding machine, the other end of the linear displacement sensor 2 is mounted on a movable plasticizing screw support frame, and the linear displacement sensor 2 is used for collecting screw displacement information. The load cell pressure sensor 3 is arranged at the end edge part of the screw, and the load cell pressure sensor 3 is used for collecting the stress information of the screw. The injection molding machine working condition acquisition device is used for acquiring injection molding working condition information, and can be randomly arranged on the injection molding machine, wherein the injection molding working condition information specifically comprises an injection speed, a minimum padding, a V/P conversion point and raw material process conditions, and the raw material process conditions comprise performance indexes such as a melt index.
In this embodiment, the microprocessor 4 is configured to convert the screw displacement information and the screw stress information from analog signals to digital signals, perform fitting processing on the screw displacement information and the screw stress information to form injection molding process data, form injection molding input data by combining the injection molding process data and the injection molding condition information, output the wear degree of the check valve, set different levels of wear state thresholds, and determine the wear state of the check valve according to the wear degree of the check valve and the different levels of wear state thresholds.
During actual application, the microprocessor 4 extracts data characteristics based on injection molding process data and combines injection molding working condition information to obtain an injection molding characteristic set, the injection molding characteristic set is used as injection molding input data, the abrasion degree of the check valve is predicted and output through a check valve abrasion state evaluation model, the microprocessor 4 sets abrasion state thresholds of different grades, whether the check valve of the current injection molding machine is abraded or not is determined according to the abrasion state thresholds of different grades, the abrasion of the current check valve can be accurately estimated, namely the abrasion state of the check valve is determined, and detection and maintenance are arranged in time. The data characteristics comprise the maximum value, the mean value, the covariance, the skewness and the single injection molding power consumption.
In the present embodiment, the terminal device 5 is used to display the check valve wear state. The terminal device 5 may be a desktop computer, a notebook computer, a smart phone, a PDA handheld terminal, a tablet computer, or other terminals with a display function.
Example 2
As shown in fig. 3, the embodiment provides a method for online monitoring the wear status of a check valve of an injection molding machine, which comprises the following steps:
and (3) acquiring injection molding data: screw displacement information, screw stress information and injection molding working condition information are collected. In practical application, screw displacement information is obtained through the linear displacement sensor 2, screw stress information is obtained through the load cell pressure sensor 3, and injection molding working condition information of the current injection molding machine is obtained through the injection molding machine working condition acquisition device;
acquiring and processing injection molding data: and converting the screw displacement information and the screw stress information from analog signals into digital signals, and performing fitting processing based on the screw displacement information and the screw stress information to form injection molding process data, wherein the injection molding process data comprises a load cell pressure curve and a screw displacement curve.
An injection molding characteristic set generation step: extracting data characteristics based on the injection molding process data and performing characteristic vectorization by combining injection molding working condition information to obtain an injection molding characteristic set; the data characteristics comprise the maximum value, the mean value, the covariance, the skewness and the single injection molding power consumption.
Predicting the abrasion state of the check valve: and predicting based on the injection feature set and combined with the check valve wear state evaluation model to determine the wear state of the check valve.
In the embodiment, the abrasion state of the check valve of the injection molding machine is obtained by monitoring the abrasion state of the check valve on line by a method for monitoring the abrasion state of the check valve on line, and then predictive maintenance is performed according to the abrasion state of the check valve.
In this embodiment, the step of generating the injection molding feature set specifically includes the following steps:
extracting injection molding process data, extracting first data characteristics, forming a first injection molding data characteristic matrix based on the first data characteristics, and performing characteristic vectorization on the first injection molding data characteristic matrix to obtain a first characteristic vector of a single injection molding sample;
calculating the power consumption of single injection by adopting an injection power consumption formula in combination with a load cell pressure curve and a screw displacement curve;
the injection molding power consumption formula is specifically as follows:
w＝∫floadcell(t)·f’position(t)dt
wherein f isloadcell(t) represents a load cell pressure curve function, f'position(t) represents screw speed, w represents screw work of single injection molding, and t represents time variable;
adding the screw work w of single injection molding into the first characteristic vector of the injection molding sample to obtain a second characteristic vector of the injection molding sample, and performing characteristic vectorization by combining the second characteristic vector of the injection molding sample and injection molding condition information to form a third characteristic vector of the injection molding sample;
and integrating the third feature vectors of all injection molding samples into one injection molding feature set. .
The embodiment also provides a method for establishing the check valve wear state evaluation model, which comprises the following steps:
a wear state simulation step: the check valves with different degrees of wear defects are manufactured respectively to simulate the check valves with different degrees of wear states, and the check valves with different wear states are simulated by forming notches with different depths between the bolt rubber ring and the injection rubber medium;
a training data acquisition step: screw displacement information, screw stress information and injection molding condition information are acquired under different wear states of the check valve.
Training data acquisition and processing steps: and converting the screw displacement information and the screw stress information from analog signals into digital signals, and performing fitting processing based on the screw displacement information and the screw stress information to form injection molding process data, wherein the injection molding process data comprises a load cell pressure curve and a screw displacement curve.
A training set generation step: extracting data characteristics based on the injection molding process data, performing characteristic vectorization by combining injection molding working condition information to obtain an injection molding characteristic set, and forming an injection molding training set by using the abrasion degree of the check valve as a training label;
training: and establishing a check valve wear state evaluation model by using a machine learning algorithm, and finishing training when the preset training times are reached and the test accuracy value of the check valve wear degree reaches a preset test accuracy threshold value, thus obtaining the trained check valve wear state evaluation model.
In the implementation, the training data acquisition step specifically sets the injection molding machine to acquire data of all samples under the process conditions of the same temperature, the same injection speed, the same material and the like, so as to obtain a load cell pressure curve, a screw displacement curve and injection molding condition information. In practical application, the material is high density polyethylene HDPE with the same grade.
In this embodiment, the training set generating step specifically includes the following steps:
extracting data characteristics from each group of injection molding process data, wherein the data characteristics comprise a maximum value, a mean value, covariance and skewness, J represents a variable, and J represents the number of the variables;
the most value is extracted by adopting a first extraction formula:
σ＝[σj1，σj2]∈RJ×2；
σj1＝max xj(k)，k＝1，2，…，K；
σj2＝min xj(k)，k＝1，2，…，K；
σ represents the maximum value of the injection molding process data;
the mean value is extracted by adopting a second extraction formula:
μ∈RJ×1；
μ represents the mean of the injection molding process data;
the covariance is extracted by using a third extraction formula:
Σ∈RJ×J；
Σ represents the covariance of the injection molding process data;
and extracting skewness by adopting a fourth extraction formula:
γ∈RJ×1；
gamma represents the skewness of the injection molding process data;
forming an injection molding data characteristic matrix based on the data characteristics:
performing feature vectorization on the injection molding data feature matrix, namely performing feature vectorization on the injection molding data feature matrix
Is flat as
Finally, forming a characteristic vector of the injection molding sample:
and calculating the power consumption of single injection molding by combining the load cell pressure curve, the screw displacement curve and the injection molding working condition information and adopting an injection molding power consumption formula:
w＝∫floadcell(t)·f’position(t)dt
wherein f isloadcell(t) represents a load cell pressure curve function, f'position(t) represents the derivative of the screw displacement curve function, namely the screw speed, and w represents the screw work of single injection molding;
adding screw work w of single injection molding to characteristic vector of injection molding sample
In the method, the characteristic vector P of each injection molding sample is formed by combining the injection molding condition information1×mIntegrating the feature vectors of all injection molding samples into an injection molding feature set
Label omega added with injection molding feature setn×1Wherein the label ω of the injection feature setn×1Specifically, the wear states are different grades, and n and m are positive integers;
performing data mining on the injection molding feature set by using a machine learning algorithm to form an injection molding training set Dn×(m+1)。
In the present embodiment, the machine learning algorithm is preferably SVR, i.e. support vector regression algorithm. The SVR adopts an epsilon-insensitive function and a kernel function algorithm to construct a linear decision function in a high-dimensional space to realize linear regression. In order to adapt to the nonlinearity of the training sample set, the SVR adopts a kernel function to solve the problem that the traditional fitting method increases the risk of overfitting when the adjustable parameters are increased. The kernel function is used for replacing a linear term in a linear equation, so that the original linear algorithm can be subjected to nonlinear regression, and nonlinear regression can be performed. Meanwhile, the kernel function is introduced, so that the purpose of dimension increasing is achieved, and overfitting can be controlled when adjustable parameters are added.
In practical application, the trained check valve wear state evaluation model is used for monitoring the check valve wear state on line, so that whether the check valve of the current injection molding machine is worn or not can be determined, and the wear of the current check valve in which grade can be accurately estimated.
In this embodiment, the wear state of the non-return valve is determined, specifically: setting different levels of abrasion state threshold values, outputting the abrasion degree of the check valve by the trained check valve abrasion state evaluation model, and determining the abrasion state of the check valve according to the abrasion degree of the check valve and the different levels of abrasion state threshold values.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.
Claims (10)
1. The device for monitoring the abrasion state of the check valve of the injection molding machine on line is provided with a microprocessor and is characterized by further comprising a linear displacement sensor, a load cell pressure sensor, an injection molding machine working condition acquisition device and a terminal device, wherein the microprocessor is respectively connected with the linear displacement sensor, the load cell pressure sensor, the injection molding machine working condition acquisition device and the terminal device;
the linear displacement sensor, the load cell pressure sensor and the injection molding machine working condition acquisition device are all arranged on the injection molding machine, the linear displacement sensor is used for acquiring screw displacement information, the load cell pressure sensor is used for acquiring screw stress information, and the injection molding machine working condition acquisition device is used for acquiring injection molding working condition information;
the microprocessor is used for outputting the abrasion degree of the check valve, setting different levels of abrasion state thresholds and determining the abrasion state of the check valve according to the abrasion degree of the check valve and the different levels of abrasion state thresholds;
the terminal equipment is used for displaying the abrasion state of the check valve.
2. The apparatus for on-line monitoring of the abrasion state of a check valve of an injection molding machine according to claim 1, wherein the linear displacement sensor is provided at a side of a distal end of the screw.
3. The apparatus for on-line monitoring of the wear state of a check valve of an injection molding machine according to claim 1, wherein the load cell pressure sensor is provided at a tip edge portion of the screw.
4. The apparatus for on-line monitoring of the wear state of the check valve of the injection molding machine according to claim 1, wherein the injection molding machine operating condition acquisition device is arbitrarily disposed on the injection molding machine.
5. The apparatus for online monitoring of the wear status of a check valve of an injection molding machine according to claim 1, wherein the injection molding condition information specifically includes injection speed, minimum pad, V/P conversion point and raw material process conditions.
6. The apparatus for on-line monitoring of the wear status of a check valve of an injection molding machine according to claim 5, wherein the raw material process conditions include melt index performance indicators.
7. A method for monitoring the abrasion state of a check valve of an injection molding machine on line is characterized by comprising the following steps:
and (3) acquiring injection molding data: acquiring screw displacement information, screw stress information and injection molding working condition information;
acquiring and processing injection molding data: converting the screw displacement information and the screw stress information from analog signals into digital signals, and performing fitting processing based on the screw displacement information and the screw stress information to form injection molding process data, wherein the injection molding process data comprises a load cell pressure curve and a screw displacement curve;
an injection molding characteristic set generation step: extracting data characteristics based on injection molding process data and performing characteristic vectorization by combining injection molding working condition information to obtain an injection molding characteristic set, wherein the data characteristics comprise a maximum value, a mean value, a covariance, a skewness and power consumption of single injection molding;
predicting the abrasion state of the check valve: and predicting based on the injection molding feature set and a check valve wear state evaluation model after machine learning training, and determining the wear state of the check valve.
8. The method for on-line monitoring of the abrasion state of the check valve of the injection molding machine according to claim 7, wherein the training data acquisition step specifically sets the injection molding machine to acquire at the same temperature, the same injection speed and the same material.
9. The method for monitoring the abrasion state of the check valve of the injection molding machine on line according to claim 7, wherein the step of generating the injection molding characteristic set specifically comprises the following steps:
extracting injection molding process data, extracting first data characteristics, forming a first injection molding data characteristic matrix based on the first data characteristics, and performing characteristic vectorization on the first injection molding data characteristic matrix to obtain a first characteristic vector of a single injection molding sample;
and calculating the power consumption of single injection molding by combining a load cell pressure curve and a screw displacement curve and adopting an injection molding power consumption formula, wherein the injection molding power consumption formula specifically comprises the following steps:
w＝∫floadcell(t)·f’position(t)dt
wherein f isloadcell(t) represents a load cell pressure curve function, f'position(t) represents screw speed, w represents screw work of single injection molding, and t represents time variable;
adding the screw work w of single injection molding into the first characteristic vector of the injection molding sample to obtain a second characteristic vector of the injection molding sample, and performing characteristic vectorization by combining the second characteristic vector of the injection molding sample and injection molding condition information to form a third characteristic vector of the injection molding sample;
and integrating the third feature vectors of all injection molding samples into one injection molding feature set.
10. The method of on-line monitoring the wear state of a check valve of an injection molding machine according to claim 7, wherein in the check valve wear state prediction step, the machine learning trained check valve wear state estimation model is established by the steps of:
a wear state simulation step: the check valves with different degrees of wear defects are manufactured respectively to simulate the check valves with different degrees of wear states, and the check valves with different wear states are simulated by forming notches with different depths between the bolt rubber ring and the injection rubber medium;
a training data acquisition step: acquiring screw displacement information, screw stress information and injection molding condition information under different wear states of the check valve;
training data acquisition and processing steps: converting the screw displacement information and the screw stress information from analog signals into digital signals, and performing fitting processing based on the screw displacement information and the screw stress information to form injection molding process data, wherein the injection molding process data comprises a load cell pressure curve and a screw displacement curve;
a training set generation step: extracting data characteristics based on the injection molding process data, performing characteristic vectorization by combining injection molding working condition information to obtain an injection molding characteristic set, and forming an injection molding training set by using the abrasion degree of the check valve as a training label;
training: and establishing a check valve wear state evaluation model by using a machine learning algorithm, and finishing training when the preset training times are reached and the test accuracy value of the check valve wear degree reaches a preset test accuracy threshold value, thus obtaining the trained check valve wear state evaluation model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356075.3A CN113085120B (en) | 2021-04-01 | 2021-04-01 | Device and method for online monitoring of wear status of check valve of injection molding machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110356075.3A CN113085120B (en) | 2021-04-01 | 2021-04-01 | Device and method for online monitoring of wear status of check valve of injection molding machine |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113085120A true CN113085120A (en) | 2021-07-09 |
| CN113085120B CN113085120B (en) | 2025-04-01 |
Family
ID=76672750
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110356075.3A Active CN113085120B (en) | 2021-04-01 | 2021-04-01 | Device and method for online monitoring of wear status of check valve of injection molding machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113085120B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114034276A (en) * | 2021-11-03 | 2022-02-11 | 珠海格力智能装备有限公司 | Deformation analysis method for plasticizing seat of injection molding machine |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101318371A (en) * | 2007-06-05 | 2008-12-10 | 发那科株式会社 | Injection molding machine |
| CN107364097A (en) * | 2016-05-12 | 2017-11-21 | 发那科株式会社 | The wear extent estimating device and abrasion method of estimating rate of the check-valves of injection machine |
| CN215203346U (en) * | 2021-04-01 | 2021-12-17 | 华南理工大学 | A device for online monitoring of wear state of check valve of injection molding machine |
-
2021
- 2021-04-01 CN CN202110356075.3A patent/CN113085120B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101318371A (en) * | 2007-06-05 | 2008-12-10 | 发那科株式会社 | Injection molding machine |
| CN107364097A (en) * | 2016-05-12 | 2017-11-21 | 发那科株式会社 | The wear extent estimating device and abrasion method of estimating rate of the check-valves of injection machine |
| CN215203346U (en) * | 2021-04-01 | 2021-12-17 | 华南理工大学 | A device for online monitoring of wear state of check valve of injection molding machine |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114034276A (en) * | 2021-11-03 | 2022-02-11 | 珠海格力智能装备有限公司 | Deformation analysis method for plasticizing seat of injection molding machine |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113085120B (en) | 2025-04-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105335692A (en) | Tire X-ray image detection and identification method and system | |
| CN102081020A (en) | Material fatigue-life predicting method based on support vector machine | |
| Wang et al. | Remaining useful life prediction based on improved temporal convolutional network for nuclear power plant valves | |
| CN108106846B (en) | A method for identification of rolling bearing fault damage degree | |
| CN106769032B (en) | Method for predicting service life of slewing bearing | |
| CN111752147B (en) | A multi-condition process monitoring method with continuous learning ability to improve PCA | |
| CN115526515B (en) | Safety monitoring system of gate for water conservancy and hydropower | |
| CN115982896B (en) | Bearing retainer service life detection method and device | |
| CN113085120A (en) | Device and method for online monitoring abrasion state of check valve of injection molding machine | |
| CN103940662B (en) | The Forecasting Methodology of high-temperature material stress relaxation residual stress and damage | |
| CN117252878B (en) | Image defect detection method of nano-imprint mold | |
| CN109635879B (en) | Coal mining machine fault diagnosis system with optimal parameters | |
| CN117058414A (en) | Online monitoring and early warning method and system for oil particles | |
| CN116383739A (en) | Intelligent Fault Diagnosis Method Based on Domain Adaptive Multimodal Data Fusion | |
| CN118861831B (en) | Research and development data processing system based on plastic product | |
| CN114004059B (en) | Health portrait method for hydroelectric generating set | |
| Zhang | Development of an in-process Pokayoke system utilizing accelerometer and logistic regression modeling for monitoring injection molding flash | |
| CN215203346U (en) | A device for online monitoring of wear state of check valve of injection molding machine | |
| CN117055509B (en) | Method for predicting short-process steel process parameters based on artificial intelligence | |
| CN117853085A (en) | Predictive maintenance based on vibration and sound for monitoring lifting system | |
| CN110174409B (en) | Medium plate periodic defect control method based on real-time detection result | |
| CN115687984A (en) | Method for monitoring health state of stirring kettle | |
| CN102608303A (en) | Online rubber hardness measurement method | |
| Rebekah et al. | AI Based Data Augmentation Process Used to Find the Defect in Injection Molding | |
| CN105096054A (en) | Injection molding machine management decision method based on overall equipment capacity and overall equipment effectiveness |
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 |