CN117147070A - Air tightness detection system and detection method for tubular medical instrument - Google Patents
Air tightness detection system and detection method for tubular medical instrument Download PDFInfo
- Publication number
- CN117147070A CN117147070A CN202311411646.4A CN202311411646A CN117147070A CN 117147070 A CN117147070 A CN 117147070A CN 202311411646 A CN202311411646 A CN 202311411646A CN 117147070 A CN117147070 A CN 117147070A
- Authority
- CN
- China
- Prior art keywords
- module
- tubular medical
- helium
- medical instrument
- detection
- 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.)
- Pending
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 85
- 239000001307 helium Substances 0.000 claims abstract description 116
- 229910052734 helium Inorganic materials 0.000 claims abstract description 116
- SWQJXJOGLNCZEY-UHFFFAOYSA-N helium atom Chemical compound [He] SWQJXJOGLNCZEY-UHFFFAOYSA-N 0.000 claims abstract description 116
- 238000013461 design Methods 0.000 claims abstract description 16
- 239000000463 material Substances 0.000 claims abstract description 16
- 238000005259 measurement Methods 0.000 claims abstract description 9
- 238000000034 method Methods 0.000 claims abstract description 9
- 239000007789 gas Substances 0.000 claims abstract description 8
- 230000006870 function Effects 0.000 claims description 27
- 238000012549 training Methods 0.000 claims description 17
- 230000004913 activation Effects 0.000 claims description 15
- 210000002569 neuron Anatomy 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 239000003550 marker Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 238000007789 sealing Methods 0.000 abstract description 2
- 238000012360 testing method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 6
- 238000010200 validation analysis Methods 0.000 description 5
- 239000007788 liquid Substances 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000036512 infertility Effects 0.000 description 3
- 238000011156 evaluation Methods 0.000 description 2
- 238000001802 infusion Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 210000002784 stomach Anatomy 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 238000005299 abrasion Methods 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 239000000700 radioactive tracer Substances 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
- G01M3/20—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using special tracer materials, e.g. dye, fluorescent material, radioactive material
- G01M3/22—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using special tracer materials, e.g. dye, fluorescent material, radioactive material for pipes, cables or tubes; for pipe joints or seals; for valves; for welds; for containers, e.g. radiators
- G01M3/222—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using special tracer materials, e.g. dye, fluorescent material, radioactive material for pipes, cables or tubes; for pipe joints or seals; for valves; for welds; for containers, e.g. radiators for tubes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
- G01B11/022—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness by means of tv-camera scanning
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/08—Measuring arrangements characterised by the use of optical techniques for measuring diameters
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/774—Generating sets of training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/82—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using neural networks
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Examining Or Testing Airtightness (AREA)
Abstract
The application provides an air tightness detection system and method for tubular medical instruments, and belongs to the technical field of sealing detection of tubular medical instruments. The air tightness detection system comprises a support frame, a measurement module, a detection module, a sliding module, a parameter determination module and a helium supply module, wherein the detection module is arranged on the sliding module and is used for driving the detection module to move along the axial direction of the tubular medical instrument so as to carry out comprehensive air leakage detection on the tubular medical instrument; the support frame is used for bearing the measuring module, the sliding module, the parameter determining module and the helium gas supplying module, and the measuring module is used for calculating the diameter size and the length size of the tubular medical instrument by collecting the images of the tubular medical instrument; the parameter determining module is used for determining optimal helium filling pressure, helium filling time, helium holding time and detection module moving speed according to the length, diameter, material, design pressure and instrument type parameters of the tubular medical instrument.
Description
Technical Field
The application relates to the technical field of sealing detection of tubular medical instruments, in particular to an air tightness detection system and method for tubular medical instruments.
Background
Most of the devices currently on the market for performing tightness tests on tubular medical instruments generally use gas or liquid as the test medium. The sterility requirements of tubular medical devices are more stringent than conventional catheters. When the liquid is used for testing, due to the viscosity of the liquid, some liquid residues can possibly be caused to be not completely removed after the testing is finished, so that the sterility requirement of the tubular medical instrument is seriously influenced, and meanwhile, the cost of subsequent cleaning is increased. Although the use of conventional gases for tightness testing does not affect sterility requirements, since the leak points on tubular medical devices are typically very small, it is difficult to visually and quickly observe and mark by gas leakage for subsequent maintenance work.
In the prior art, publication number CN116429336a describes a leak testing device and method that can slide along a tubular medical instrument by attaching to the outer surface of the medical instrument to detect and mark the leak point of the medical instrument. However, this prior art requires a high degree of complete fit of the device, and the central aperture diameter of the device is fixed and cannot accommodate tubular medical instruments of different diameters. In addition, the prior art does not consider the setting of parameters such as helium filling pressure, helium filling time, helium holding time, and movement speed of the detection module, and the difference of these parameters may affect the test effect. In view of the above, we propose an airtight detection system and detection method for tubular medical devices.
Disclosure of Invention
In order to overcome a series of defects existing in the prior art, an object of the present application is to provide an airtight detection system for a tubular medical apparatus, which comprises a support frame, a measurement module, a detection module, a sliding module, a parameter determination module and a helium supply module, wherein the detection module is installed on the sliding module, and the sliding module is used for driving the detection module to move along the axial direction of the tubular medical apparatus so as to perform comprehensive air leakage detection on the tubular medical apparatus; the support frame is used for bearing the measuring module, the sliding module, the parameter determining module and the helium gas supplying module, and the measuring module is used for calculating the diameter size and the length size of the tubular medical instrument by collecting the images of the tubular medical instrument; the parameter determining module is used for determining optimal helium filling pressure, helium filling time, helium holding time and moving speed of the detecting module according to parameters of the length, diameter, material, design pressure and instrument type of the tubular medical instrument; the helium supply module is used for helium filling the tubular medical instrument according to the parameters output by the parameter determination module.
Further, the measurement module includes.
And the camera is arranged on the supporting frame and used for collecting images of the tubular medical instrument.
And the computer vision processing unit is used for calculating the diameter size and the length size of the tubular medical instrument by utilizing the image captured by the camera and an edge detection algorithm so as to provide data support for subsequent processing.
Further, the parameter determining module includes.
And the training unit is used for preparing the obtained historical experimental data into a data set, and dividing the data set into a training set and a verification set to construct a prediction model.
The parameter determining unit is used for determining a helium filling and detecting scheme according to specific parameters of the tubular medical instrument; the diameter and length data of the tubular medical instrument, corresponding material parameters, design pressure and instrument types (such as a catheter, a stomach tube, an infusion set and the like) measured by the measuring module are input into the constructed prediction model, so that the optimal helium filling pressure, helium filling time, helium holding time and moving speed of the detecting module are obtained.
Further, the historical experimental data comprise the length, diameter, material, design pressure, instrument type of the tubular medical instrument, and the corresponding optimal helium filling pressure, optimal helium filling time, helium holding time and detection module moving speed; the training unit divides the historical experimental data into a training set and a verification set, a prediction model is trained based on a fully-connected neural network algorithm, the input of the prediction model is the parameter of the tubular medical instrument, and the output is the optimal helium filling and detecting scheme.
Further, the prediction model is based on a fully connected neural network algorithm, and specifically comprises the following steps.
Input layer: including 5 neurons, for receiving input features.
First hidden layer: including 64 neurons, the activation function is a ReLU activation function, and overfitting is prevented by adding Dropout layers.
Second hidden layer: including 64 neurons, the activation function is a ReLU activation function, and overfitting is prevented by adding Dropout layers.
Output layer: comprises 4 neurons, the output function is a linear activation function, and the loss function is a smooth L 1 Loss L 1 =1/n Σ|y- ŷ |, where y is the true value, ŷ is the predicted value, and n is the number of samples.
An optimizer: using Adam optimizer, the initial learning rate is 0.001 and decays according to the change of the loss function, the tuning unit uses grid search to traverse all possible hyper-parameter combinations and uses mean square error as an index to select the minimized hyper-parameter combination.
Further, the detection module comprises a shell, a circular through hole is formed in the center of the shell so that a tubular medical instrument can pass through the shell, a plurality of helium suction guns with adjustable positions are uniformly arranged in the shell, and a plurality of marker pens and a depth camera are further fixed on the shell.
Further, the helium suction guns are in one-to-one correspondence with the marker pens, thereby facilitating marking of the leak location when a leak is detected.
The application also aims to provide a method for detecting the air tightness of the tubular medical instrument, which comprises the following steps.
Step S1, obtaining the diameter size and the length size of the tubular medical instrument through the image acquired by the camera.
And S2, determining the position of the detection module and the helium suction gun inside the detection module through the depth camera and the diameter size of the tubular medical instrument.
And S3, determining the optimal helium filling pressure, helium filling time, helium holding time and detection module moving speed required by detection according to the diameter size, the length size, the material, the design pressure and the instrument type of the tubular medical instrument.
And S4, controlling the operation of the helium supply module and the sliding module through the optimal helium filling pressure, the optimal helium filling time, the optimal helium holding time and the optimal detection module moving speed so as to detect the air tightness of the tubular medical instrument.
And S5, when the helium suction gun detects helium, indicating that a leakage point exists, slowing down the moving speed of the detection module so as to mark the leakage point, and recovering the moving speed of the detection module after marking is finished.
Further, by changing the position of the helium suction gun so that the distance between the helium suction gun and the tubular medical instrument is smaller than 1mm, whether the tubular medical instrument leaks air or not can be detected conveniently.
Compared with the prior art, the application has at least the following technical effects or advantages.
The application adopts helium as the tracer gas to detect the air tightness of the tubular medical instrument, and has the following advantages: the detection device does not need to be completely attached to the outer surface of the tubular medical instrument, so that the application range is enlarged, and the equipment abrasion during operation is reduced; the helium suction gun with adjustable positions is adopted, the detection aperture can be adjusted according to tubular medical instruments with different diameters, and the detection applicability is enlarged; by applying the machine learning method, the optimal helium filling parameters are learned from the historical data, the uncertainty of determining the parameters by relying on experience in the past is avoided, and the accuracy and the efficiency of detection are improved.
Drawings
Fig. 1 is a schematic structural diagram of an airtight detection system for a tubular medical instrument according to an embodiment of the present application.
Fig. 2 is a schematic structural diagram of a measurement module according to an embodiment of the application.
Fig. 3 is a schematic structural diagram of a parameter determining module according to an embodiment of the present application.
Fig. 4 is a schematic diagram of a neural network according to an embodiment of the application.
Fig. 5 is a schematic structural diagram of a detection module according to an embodiment of the application.
FIG. 6 is a graph showing the comparison of predicted values and actual values of a prediction model according to an embodiment of the present application.
FIG. 7 is an evaluation index diagram of a prediction model in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application become more apparent, the technical solutions in the embodiments of the present application will be described in more detail below with reference to the accompanying drawings in the embodiments of the present application. In the drawings, the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions throughout. The described embodiments are some, but not all, embodiments of the application.
All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
The embodiments described below, together with the words of orientation, are exemplary and intended to explain the application and should not be taken as limiting the application.
Referring to fig. 1 and 2, an embodiment of the present application provides an airtight detection system for a tubular medical apparatus, including a support frame, a measurement module, a detection module, a sliding module, a parameter determination module, and a helium supply module, where the detection module is installed on the sliding module, and the sliding module is used to drive the detection module to move along an axial direction of the tubular medical apparatus so as to perform comprehensive air leakage detection on the tubular medical apparatus; the support frame is used for bearing the measuring module, the sliding module, the parameter determining module and the helium gas supplying module, and the measuring module is used for calculating the diameter size and the length size of the tubular medical instrument by collecting the images of the tubular medical instrument; the parameter determining module is used for determining optimal helium filling pressure, helium filling time, helium holding time and detection module moving speed according to the length, diameter, material, design pressure and instrument type parameters of the tubular medical instrument.
And the helium supply module is used for charging helium into the tubular medical instrument according to the parameters output by the parameter determination module.
In this embodiment, the diameter size and the length size of the tubular medical apparatus can be obtained by the measurement module, and the position of the detection module can be determined by the detection module; the distance between the helium suction gun and the tubular medical instrument is smaller than 1mm by changing the moving distance of the helium suction gun so as to be convenient for detecting whether the tubular medical instrument leaks air or not; inputting the diameter size and the length size of the tubular medical instrument obtained by the measuring module into a prediction model by combining the material, the design pressure and the instrument type of the tubular medical instrument to obtain proper helium filling pressure, helium filling time, helium holding time and the moving speed of the detecting module, controlling the helium supply module and the detecting module to detect the air tightness of the tubular medical instrument by using the output parameters, slowing down the moving speed of the detecting module and marking the position when the helium suction gun detects abnormality, and recovering the moving speed of the detecting module after marking is completed.
Referring to fig. 1 and 3, the measurement module includes.
And the camera is arranged on the supporting frame and used for collecting images of the tubular medical instrument.
And the computer vision processing unit is used for calculating the diameter size and the length size of the tubular medical instrument by utilizing the image captured by the camera and an edge detection algorithm so as to provide data support for subsequent processing.
Referring to fig. 1, 4 and 5, the parameter determination module includes.
And the training unit is used for preparing the obtained historical experimental data into a data set, and dividing the data set into a training set and a verification set to construct a prediction model.
The parameter determining unit is used for determining a helium filling and detecting scheme according to specific parameters of the tubular medical instrument; the diameter and length data of the tubular medical instrument, corresponding material parameters, design pressure and instrument types (such as a catheter, a stomach tube, an infusion set and the like) measured by the measuring module are input into the constructed prediction model, so that the optimal helium filling pressure, helium filling time, helium holding time and moving speed of the detecting module are obtained.
Further, the historical experimental data comprise the length, diameter, material, design pressure, instrument type of the tubular medical instrument, and the corresponding optimal helium filling pressure, optimal helium filling time, helium holding time and detection module moving speed; the training unit divides the historical experimental data into a training set and a verification set, a prediction model is trained based on a fully-connected neural network algorithm, the input of the prediction model is the parameter of the tubular medical instrument, and the output is the optimal helium filling and detecting scheme.
Further, the prediction model is based on a fully connected neural network algorithm, and specifically comprises the following steps.
Training the fully connected neural network model to achieve prediction of tubular medical device parameters to relevant output parameters specifically includes the following steps.
Data collection and preparation.
Data including the length, diameter, material, design pressure, instrument type, and corresponding optimal helium filling pressure, optimal helium filling time, helium hold time, and detection module movement speed of the tubular medical instrument is collected.
The data is cleaned and preprocessed, including processing missing values, normalizing numerical features, monothermally encoding classification features, and the like.
And (5) data segmentation.
The data set was divided into training and validation sets at a ratio of 80%, 20%.
And constructing a neural network model.
Input layer: including 5 neurons, for receiving input features.
First hidden layer: including 64 neurons, the activation function is a ReLU activation function, and overfitting is prevented by adding Dropout layers.
Second hidden layer: including 64 neurons, the activation function is a ReLU activation function, and overfitting is prevented by adding Dropout layers.
Output layer: comprises 4 neurons, the output function is a linear activation function, and the loss function is a smooth L 1 Loss L 1 =1/n Σ|y- ŷ |, where y is the true value, ŷ is the predicted value, and n is the number of samples.
An optimizer: using Adam optimizer, the initial learning rate is 0.001 and decays according to the change of the loss function, the tuning unit uses grid search to traverse all possible hyper-parameter combinations and uses mean square error as an index to select the minimized hyper-parameter combination.
And compiling a model.
Defining the loss function uses Mean Square Error (MSE).
Random gradient descent (SGD) was chosen as the optimization algorithm.
The determination coefficient (R2) is added as a model performance index.
And training a model.
The model is trained using a training dataset, and during the training process, the model continuously adjusts the weights to reduce the value of the loss function.
Performance on the validation set is monitored to avoid overfitting.
And (5) evaluating a model.
The performance of the model is evaluated using the validation set. The loss and performance index of the model on the validation data are calculated.
In this example, 600 sets of data were collected, 80% of the data were randomly selected to train the predictive model, and the remaining 20% of the data were used to validate the predictive model. Fig. 6 is a graph showing a comparison of a predicted value and a true value of a prediction model, wherein an abscissa represents the true value predicted by the model, an ordinate represents the corresponding predicted value, each point represents a sample, an abscissa of the point represents the true value of the sample, and an ordinate of the point represents the predicted value of the sample. As can be seen from FIG. 6, the sample points are mainly distributed near the diagonal, which indicates that the overall prediction effect of the prediction model is good, and the predicted value can better reflect the magnitude and the variation trend of the true value.
FIG. 7 is a graph of evaluation indicators for a predictive model, which indicate that the model performs well on validation data: the Mean Square Error (MSE) is 0.002 and is close to zero, the Root Mean Square Error (RMSE) is 0.045 and is relatively small, the judgment coefficient (R) is 0.98 and is close to 1, and the model can be better fit data.
Referring to fig. 1, 2 and 5, the detection module includes a housing, a circular through hole is formed in the center of the housing so that a tubular medical instrument can pass through the circular through hole, a plurality of helium suction guns are uniformly arranged in the housing, and a plurality of marker pens and a depth camera are further fixed on the housing.
In the embodiment, the helium suction gun is used for detecting whether leakage of helium exists or not, the extension length of the helium suction gun is adjustable so as to adapt to tubular medical instruments with different diameters, and the helium suction gun corresponds to the marker pen one by one, so that the leakage position can be marked conveniently when the leakage is detected; the depth camera is used for detecting the distance H from the upper edge of the outer surface of the tubular medical instrument to the camera and the distance H from the table surface of the support frame to the camera, and the central height H' =H-h+d/2 of the tubular medical instrument can be calculated by combining the diameter d of the tubular medical instrument, so that the position of the detection module is determined, and the extension length of the helium suction gun is further determined.
The application also discloses a detection method of the air tightness detection system for the tubular medical instrument, which comprises the following steps.
Step S1, obtaining the diameter size and the length size of the tubular medical instrument through the image acquired by the camera.
And S2, determining the position of the detection module and the helium suction gun inside the detection module through the depth camera and the diameter size of the tubular medical instrument.
And S3, determining the optimal helium filling pressure, helium filling time, helium holding time and detection module moving speed required by detection according to the diameter size, the length size, the material, the design pressure and the instrument type of the tubular medical instrument.
And S4, controlling the operation of the helium supply module and the sliding module through the optimal helium filling pressure, the optimal helium filling time, the optimal helium holding time and the optimal detection module moving speed so as to detect the air tightness of the tubular medical instrument.
And S5, when the helium suction gun detects helium, indicating that a leakage point exists, slowing down the moving speed of the detection module so as to mark the leakage point, and recovering the moving speed of the detection module after marking is finished.
In summary, when the airtight detection is performed on the tubular medical instrument, the diameter size and the length size of the tubular medical instrument to be detected are obtained through the camera of the detection module, the position of the detection module and the size of the detection aperture are determined by combining the data detected by the depth camera, the obtained diameter and the length of the tubular medical instrument are input into a trained prediction model by combining the material, the design pressure and the instrument type of the tubular medical instrument to obtain the optimal helium filling pressure, the helium filling time, the helium holding time and the movement speed of the detection module, and the helium supply module and the sliding module are controlled to operate according to the optimal helium filling pressure, the helium holding time and the movement speed of the detection module so as to perform the airtight detection on the tubular medical instrument.
Claims (9)
1. The air tightness detection system for the tubular medical instrument comprises a support frame, a measurement module, a detection module, a sliding module, a parameter determination module and a helium supply module, and is characterized in that the detection module is arranged on the sliding module and is used for driving the detection module to move along the axial direction of the tubular medical instrument so as to carry out comprehensive air leakage detection on the tubular medical instrument; the support frame is used for bearing the measuring module, the sliding module, the parameter determining module and the helium gas supplying module, and the measuring module is used for calculating the diameter size and the length size of the tubular medical instrument by collecting the images of the tubular medical instrument; the parameter determining module is used for determining optimal helium filling pressure, helium filling time, helium holding time and moving speed of the detecting module according to parameters of the length, diameter, material, design pressure and instrument type of the tubular medical instrument; the helium supply module is used for helium filling the tubular medical instrument according to the parameters output by the parameter determination module.
2. The tightness detection system for a tubular medical device according to claim 1, wherein said measurement module comprises:
the camera is arranged on the support frame and used for collecting images of the tubular medical instrument;
and the computer vision processing unit is used for calculating the diameter size and the length size of the tubular medical instrument by utilizing the image captured by the camera and an edge detection algorithm so as to provide data support for subsequent processing.
3. The tightness detection system for a tubular medical device according to claim 1, wherein said parameter determination module comprises:
the training unit is used for preparing the obtained historical experimental data into a data set, dividing the data set into a training set and a verification set and constructing a prediction model;
the parameter determining unit is used for determining a helium filling and detecting scheme according to specific parameters of the tubular medical instrument; the diameter and length data of the tubular medical instrument, corresponding material parameters, design pressure and instrument type, which are measured by the measuring module, are input into a constructed prediction model to obtain the optimal helium filling pressure, helium filling time, helium holding time and moving speed of the detecting module.
4. The tightness detection system for tubular medical devices according to claim 1, wherein the historical experimental data comprises length, diameter, material, design pressure, device type of the tubular medical device, and corresponding optimal helium filling pressure, optimal helium filling time, helium holding time, and detection module moving speed; the training unit divides the historical experimental data into a training set and a verification set, a prediction model is trained based on a fully-connected neural network algorithm, the input of the prediction model is the parameter of the tubular medical instrument, and the output is the optimal helium filling and detecting scheme.
5. The tightness detection system for a tubular medical device according to claim 1, wherein the prediction model is based on a fully connected neural network algorithm, specifically comprising:
input layer: comprising 5 neurons for receiving input features;
first hidden layer: the method comprises the steps of including 64 neurons, wherein an activation function is a ReLU activation function, and overfitting is prevented by adding a Dropout layer;
second hidden layer: the method comprises the steps of including 64 neurons, wherein an activation function is a ReLU activation function, and overfitting is prevented by adding a Dropout layer;
output layer: comprises 4 neurons, the output function is a linear activation function, and the loss function is a smooth L 1 Loss L 1 =1/n Σ|y- ŷ |, where y is the true value, ŷ is the predicted value, n is the number of samples;
an optimizer: using Adam optimizer, the initial learning rate is 0.001 and decays according to the change of the loss function, the tuning unit uses grid search to traverse all possible hyper-parameter combinations and uses mean square error as an index to select the minimized hyper-parameter combination.
6. The airtight detection system for a tubular medical instrument according to claim 1, wherein the detection module comprises a housing, a circular through hole is formed in the center of the housing so that the tubular medical instrument can pass through, a plurality of position-adjustable helium suction guns are uniformly arranged in the housing, and a plurality of marker pens and a depth camera are further fixed on the housing.
7. The airtight detection system for a tubular medical instrument according to claim 1, wherein the helium suction guns are in one-to-one correspondence with the marker pens, thereby facilitating marking of the leak location when a leak is detected.
8. The method for detecting the air tightness of the tubular medical instrument is characterized by comprising the following steps of:
step S1, obtaining the diameter size and the length size of a tubular medical instrument through images acquired by a camera;
s2, determining the position of a detection module and an internal helium suction gun thereof through the diameter sizes of the depth camera and the tubular medical instrument;
step S3, determining the optimal helium filling pressure, helium filling time, helium holding time and detection module moving speed required by detection by combining the diameter size, the length size, the material, the design pressure and the instrument type of the tubular medical instrument;
s4, controlling the operation of the helium supply module and the sliding module through the optimal helium filling pressure, the optimal helium filling time, the optimal helium holding time and the optimal detection module moving speed so as to detect the air tightness of the tubular medical instrument;
and S5, when the helium suction gun detects helium, indicating that a leakage point exists, slowing down the moving speed of the detection module so as to mark the leakage point, and recovering the moving speed of the detection module after marking is finished.
9. The method according to claim 8, wherein in step S2, the position of the helium suction gun is changed so that the distance between the helium suction gun and the tubular medical instrument is less than 1mm, so as to facilitate the detection of whether the tubular medical instrument leaks.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311411646.4A CN117147070A (en) | 2023-10-30 | 2023-10-30 | Air tightness detection system and detection method for tubular medical instrument |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311411646.4A CN117147070A (en) | 2023-10-30 | 2023-10-30 | Air tightness detection system and detection method for tubular medical instrument |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117147070A true CN117147070A (en) | 2023-12-01 |
Family
ID=88884670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311411646.4A Pending CN117147070A (en) | 2023-10-30 | 2023-10-30 | Air tightness detection system and detection method for tubular medical instrument |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117147070A (en) |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101008992A (en) * | 2006-12-30 | 2007-08-01 | 北京市劳动保护科学研究所 | Method for detecting leakage of pipeline based on artificial neural network |
| CN109506848A (en) * | 2018-12-29 | 2019-03-22 | 汉威科技集团股份有限公司 | A kind of novel online scan-type ultrasonic gas leak detection system |
| CN111089690A (en) * | 2020-03-05 | 2020-05-01 | 成都欧赛医疗器械有限公司 | Device and method for testing air tightness of tubular medical instrument |
| CN112213051A (en) * | 2020-09-03 | 2021-01-12 | 恒大恒驰新能源汽车研究院(上海)有限公司 | Air tightness detection method and device and electronic equipment |
| CN113092021A (en) * | 2021-04-01 | 2021-07-09 | 中检华通威国际检验(苏州)有限公司 | Detection device and detection method for air tightness of medical instrument |
| CN216645758U (en) * | 2022-01-24 | 2022-05-31 | 河南省医疗器械检验所 | Medical instrument gas tightness detection device |
| CN216955045U (en) * | 2021-12-31 | 2022-07-12 | 菏泽市产品检验检测研究院 | Boiler pressure pipeline detection device |
| CN115077812A (en) * | 2022-06-30 | 2022-09-20 | 徐州天力电子科技有限公司 | Electric vehicle controller seals detecting system |
| CN115999007A (en) * | 2022-12-30 | 2023-04-25 | 上海德尔格医疗器械有限公司 | Device, method and medical instrument for detecting leaks in a breathing circuit |
| CN116380366A (en) * | 2023-04-14 | 2023-07-04 | 福建嘉得利厨卫发展有限公司 | Pipe fitting air tightness testing device and testing method thereof |
| CN116429336A (en) * | 2023-06-12 | 2023-07-14 | 山东科锐医疗用品有限公司 | Tightness testing device for tubular medical instrument and application method thereof |
| CN219914773U (en) * | 2023-06-28 | 2023-10-27 | 无锡想煜科技发展有限公司 | Air tightness testing device for medical instrument |
-
2023
- 2023-10-30 CN CN202311411646.4A patent/CN117147070A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101008992A (en) * | 2006-12-30 | 2007-08-01 | 北京市劳动保护科学研究所 | Method for detecting leakage of pipeline based on artificial neural network |
| CN109506848A (en) * | 2018-12-29 | 2019-03-22 | 汉威科技集团股份有限公司 | A kind of novel online scan-type ultrasonic gas leak detection system |
| CN111089690A (en) * | 2020-03-05 | 2020-05-01 | 成都欧赛医疗器械有限公司 | Device and method for testing air tightness of tubular medical instrument |
| CN112213051A (en) * | 2020-09-03 | 2021-01-12 | 恒大恒驰新能源汽车研究院(上海)有限公司 | Air tightness detection method and device and electronic equipment |
| CN113092021A (en) * | 2021-04-01 | 2021-07-09 | 中检华通威国际检验(苏州)有限公司 | Detection device and detection method for air tightness of medical instrument |
| CN216955045U (en) * | 2021-12-31 | 2022-07-12 | 菏泽市产品检验检测研究院 | Boiler pressure pipeline detection device |
| CN216645758U (en) * | 2022-01-24 | 2022-05-31 | 河南省医疗器械检验所 | Medical instrument gas tightness detection device |
| CN115077812A (en) * | 2022-06-30 | 2022-09-20 | 徐州天力电子科技有限公司 | Electric vehicle controller seals detecting system |
| CN115999007A (en) * | 2022-12-30 | 2023-04-25 | 上海德尔格医疗器械有限公司 | Device, method and medical instrument for detecting leaks in a breathing circuit |
| CN116380366A (en) * | 2023-04-14 | 2023-07-04 | 福建嘉得利厨卫发展有限公司 | Pipe fitting air tightness testing device and testing method thereof |
| CN116429336A (en) * | 2023-06-12 | 2023-07-14 | 山东科锐医疗用品有限公司 | Tightness testing device for tubular medical instrument and application method thereof |
| CN219914773U (en) * | 2023-06-28 | 2023-10-27 | 无锡想煜科技发展有限公司 | Air tightness testing device for medical instrument |
Non-Patent Citations (1)
| Title |
|---|
| 杨卿;郭斌;罗哉;林敏;: "遗传优化神经网络在气密性检测中的应用", 传感器与微系统, no. 02 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106645570B (en) | Method and device for detecting surface defects of wind driven generator blade | |
| CN112508105B (en) | Fault detection and retrieval method for oil extraction machine | |
| CN107657603A (en) | A kind of industrial appearance detecting method based on intelligent vision | |
| CN113340598B (en) | Rolling bearing intelligent fault diagnosis method based on regularized sparse model | |
| CN111414977A (en) | Weighted integration temperature sensitive point combination selection method for machine tool spindle thermal error modeling | |
| CN110363337A (en) | A kind of pumping unit amount oil method and system based on data-driven | |
| WO2022088096A1 (en) | Method for measuring actual area of defect, and method and apparatus for testing display panel | |
| CN107748539A (en) | The multi-shaft interlocked Error Tracing ＆ method of five-axis machine tool based on the identification of RTCP error characters | |
| CN109840497A (en) | A kind of pointer-type water meter reading detection method based on deep learning | |
| CN115760837A (en) | Crystal quality evaluation method and system based on deep neural network | |
| CN106886989A (en) | The automatic optical detection method of keyboard | |
| CN115082444B (en) | Copper pipe weld defect detection method and system based on image processing | |
| CN114663744A (en) | Instrument automatic identification method and system based on machine learning | |
| CN110458809B (en) | Yarn evenness detection method based on sub-pixel edge detection | |
| CN117147070A (en) | Air tightness detection system and detection method for tubular medical instrument | |
| CN117790380A (en) | Accurate control operation method for wafer cleaning mechanical arm | |
| CN110470263A (en) | A kind of revolving body measurement system error compensation method based on gradient boosted tree | |
| Lai et al. | A novel scale recognition method for pointer meters adapted to different types and shapes | |
| CN117232452B (en) | Comparison instrument for detecting size of part and application method thereof | |
| CN111860464B (en) | Substation auxiliary monitoring system pointer reading identification compensation method and device | |
| CN206974923U (en) | refrigerator appearance quality detection system | |
| US20060203254A1 (en) | Measurements of an axisymmetric part including helical coil springs | |
| CN106871784A (en) | A kind of laser measurement method, device and system | |
| CN107946227A (en) | A kind of wafer positioning method and system based on pallet | |
| CN117829821B (en) | Cloud platform-based composite material equipment maintenance and management method |
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 |