Hot melt adhesive production control method and system

Abstract

The invention discloses a hot melt adhesive production control method and system, and relates to the technical field of hot melt adhesive production. The method comprises the following steps: performing automatic quality and uniformity detection while melting and stirring a material, and judging whether the material is uniformly mixed or not to obtain a first glue solution; filtering the first glue solution to obtain a second glue solution; conveying the second glue solution to an extruding machine, and performing extrusion forming to obtain a glue strip; and the rubber strip is cooled and cut, and the target rubber stick is obtained. Real-time monitoring and uniformity detection are performed by introducing an automatic detection technology, so that an ideal mixing effect of materials in a melting stage is ensured, the condition of excessive stirring or insufficient stirring is avoided, the time of a mixing process is shortened, and the production efficiency is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of hot melt adhesive production, and in particular to a hot melt adhesive production control method and system. Background Art

[0002] Hot melt adhesive is a solid adhesive, usually a mixture of resin, wax, oil, plasticizer and other ingredients, with good adhesion and flexibility. Unlike traditional solvent-based adhesives, hot melt adhesive does not require solvents during use, which makes it have significant advantages in environmental protection. Therefore, it is widely used in packaging, electronics, automobiles, furniture, medical devices and other industries. The production process of hot melt adhesive mainly includes steps such as raw material proportioning, mixing, heating, extrusion and cooling. In the production process, various raw materials are first mixed in a certain proportion, and then the raw materials are melted by heating to form a uniform adhesive liquid. Then, the molten adhesive liquid is processed into the desired form, such as sheets, strips or granules, by an extruder, and finally solidified by cooling equipment to form a finished product.

[0003] Although the production process of hot melt adhesive is relatively mature, the industry is currently facing the problem of more manual intervention and low automation level. Existing production control often promotes process automation by setting a fixed melting and stirring time, and usually sets a longer melting and stirring time, or performs manual sampling and testing to ensure the full fusion of materials. This greatly reduces the production efficiency of hot melt adhesive. Summary of the invention

[0004] The purpose of the present invention is to solve the problem of low production efficiency mentioned in the above background technology, and to propose a hot melt adhesive production control method and system.

[0005] A first aspect of the present invention provides a hot melt adhesive production control method, the method comprising:

[0006] According to the preset formula, the materials are transported to the reactor;

[0007] The materials are melted and stirred, and automated testing is performed simultaneously to obtain a uniformly mixed first glue solution;

[0008] filtering the first glue solution to obtain a second glue solution;

[0009] The second adhesive liquid is conveyed to an extruder for extrusion molding to obtain an adhesive strip;

[0010] The glue strip is cooled and cut to obtain a target glue stick.

[0011] Optionally, a plurality of temperature sensors are disposed at different heights in the reactor; a liquid level sensor is built into the reactor;

[0012] While the material is being melted and stirred, temperature control is performed, and the temperature control includes:

[0013] Obtaining the liquid level in the reactor through the liquid level sensor;

[0014] Obtain temperature measurement values ​​of multiple temperature sensors below the liquid surface;

[0015] The average value of the multiple temperature measurement values ​​is used as the real-time temperature in the reactor;

[0016] The temperature of the material in the reactor is controlled according to a preset temperature control algorithm and the real-time temperature.

[0017] Optionally, the temperature control is divided into a heating stage and a constant temperature stage; the melting and stirring of the materials and the simultaneous automatic detection to obtain a uniformly mixed first glue solution include:

[0018] In the constant temperature stage, obtain the viscosity change data of the material within the target period, and calculate its average value and standard deviation;

[0019] Calculating the absolute difference between the average value and the target viscosity;

[0020] The ultrasonic sensors at different positions are used to measure the propagation speed of ultrasonic waves in different areas, and the standard deviation of multiple propagation speeds is calculated;

[0021] If the absolute difference is smaller than the first threshold, the standard deviation of the viscosity is smaller than the second threshold, and the standard deviation of the propagation speed is smaller than the third threshold, the melting and stirring is terminated to obtain the first glue solution.

[0022] Optionally, the step of obtaining the viscosity change data of the material within the target period includes:

[0023] For the target sampling time, the liquid level in the reactor is obtained, and the immersion depth of the stirrer is obtained according to the liquid level; the target sampling time is any sampling time within the target time period;

[0024] Obtain the material temperature in the reactor;

[0025] Get the torque of the stirrer;

[0026] The immersion depth, material temperature and torque are used as inputs of a pre-trained viscosity prediction model to obtain the material viscosity at a target sampling time;

[0027] According to multiple sampling moments within the target period, the viscosity change data of the material is obtained.

[0028] Optionally, the viscosity prediction model is one of a multi-layer perceptron regression model, a support vector regression model and a random forest regression model.

[0029] A second aspect of the present invention provides a hot melt adhesive production control system, the system comprising:

[0030] The raw material conveying module is used to convey the materials to the reactor according to the preset formula;

[0031] The melting reaction module is used to melt and stir the materials and perform automatic detection to obtain a uniformly mixed first glue solution;

[0032] An impurity filtering module, used for filtering the first glue solution to obtain a second glue solution;

[0033] An extrusion molding module, used for conveying the second adhesive liquid to an extruder for extrusion molding to obtain an adhesive strip;

[0034] The finished product cutting module is used to cool and cut the glue strip to obtain the target glue stick.

[0035] Optionally, a plurality of temperature sensors are disposed at different heights in the reactor; a liquid level sensor is built into the reactor;

[0036] The melting reaction module includes a temperature control module, and the temperature control module includes:

[0037] A liquid level determination module, used to obtain the liquid level in the reactor through the liquid level sensor;

[0038] A multi-point temperature acquisition module is used to obtain temperature measurement values ​​of multiple temperature sensors under the liquid surface;

[0039] A temperature value determination module is used to use the average value of multiple temperature measurement values ​​as the real-time temperature in the reactor;

[0040] The automatic adjustment module is used to control the temperature of the material in the reactor according to a preset temperature control algorithm and the real-time temperature.

[0041] Optionally, the temperature control is divided into a heating stage and a constant temperature stage; the melting reaction module also includes a quality standard module; the quality standard module includes:

[0042] The delayed data acquisition module is used to obtain the viscosity change data of the material within the target period during the constant temperature stage, and calculate its average value and standard deviation;

[0043] A difference calculation module, used for calculating the absolute difference between the average value and the target viscosity;

[0044] The multi-point physical property detection module is used to measure the propagation speed of ultrasonic waves in different areas through ultrasonic sensors at different positions, and calculate the standard deviation of multiple propagation speeds;

[0045] The process control module is used to terminate the melting and stirring to obtain the first glue solution if the absolute difference is less than a first threshold, the standard deviation of the viscosity is less than a second threshold, and the standard deviation of the propagation speed is less than a third threshold.

[0046] Optionally, the delay data acquisition module includes:

[0047] An immersion depth detection module is used to obtain the liquid level in the reactor at a target sampling time, and obtain the immersion depth of the agitator according to the liquid level; the target sampling time is any sampling time within the target time period;

[0048] A temperature data acquisition module is used to obtain the material temperature in the reactor;

[0049] A torque data acquisition module, used to acquire the torque of the stirrer;

[0050] A viscosity prediction module, used to use the immersion depth, material temperature and torque as inputs of a pre-trained viscosity prediction model to obtain the material viscosity at a target sampling time;

[0051] The time period data integration module is used to obtain the material viscosity change data according to the material viscosity at multiple sampling moments within the target time period.

[0052] Optionally, the viscosity prediction model is a multi-layer perceptron regression model, a support vector regression model or a random forest regression model.

[0053] Beneficial effects of the present invention:

[0054] The present invention proposes a hot melt adhesive production control method, which includes: conveying materials to a reactor according to a preset formula; melting and stirring the materials, and simultaneously performing automatic detection to obtain a uniformly mixed first adhesive liquid; filtering the first adhesive liquid to obtain a second adhesive liquid; conveying the second adhesive liquid to a transfer tank for cooling; conveying the cooled second adhesive liquid to an extruder for extrusion molding to obtain an adhesive strip; cooling and cutting the adhesive strip to obtain a target adhesive stick.

[0055] By introducing automated detection technology for real-time monitoring and uniformity testing, we can ensure that the materials achieve the ideal mixing effect during the melting stage, avoid over-mixing or under-mixing, shorten the mixing process time, and thus improve production efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] The present invention will be further described below in conjunction with the accompanying drawings.

[0057] Figure 1 A flow chart of a hot melt adhesive production control method is provided for an embodiment of the present invention;

[0058] Figure 2 An architectural diagram of a hot melt adhesive production control system is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0060] The embodiment of the present invention provides a hot melt adhesive production control method. Figure 1 , Figure 1 A flow chart of a hot melt adhesive production control method provided by an embodiment of the present invention. The method comprises the following steps:

[0061] S101, transporting materials to the reactor according to a preset formula.

[0062] S102, melting and stirring the materials, and simultaneously performing automatic detection to obtain a uniformly mixed first glue solution.

[0063] S103, filtering the first glue solution to obtain a second glue solution.

[0064] S104, conveying the second adhesive liquid to an extruder for extrusion molding to obtain an adhesive strip.

[0065] S105, cooling and cutting the rubber strip to obtain a target rubber stick.

[0066] A hot melt adhesive production control method provided in an embodiment of the present invention introduces automated detection technology for real-time monitoring and uniformity detection to ensure that the material achieves an ideal mixing effect during the melting stage, avoids excessive or insufficient stirring, shortens the mixing process time, and thus improves production efficiency.

[0067] In one embodiment, a plurality of temperature sensors are installed at different heights in the reactor; a liquid level sensor is built into the reactor;

[0068] While the materials are being melted and stirred, the temperature is controlled. The temperature control includes:

[0069] Step 1: Obtain the liquid level in the reactor through a liquid level sensor.

[0070] Step 2: Obtain temperature measurement values ​​of multiple temperature sensors below the liquid surface.

[0071] Step 3: taking the average value of multiple temperature measurement values ​​as the real-time temperature in the reactor.

[0072] Step 4: Control the temperature of the material in the reactor according to the preset temperature control algorithm and the real-time temperature.

[0073] The liquid level sensor may be an ultrasonic liquid level sensor or a radar liquid level sensor. The temperature control algorithm may adopt a PID control algorithm.

[0074] In one implementation, multiple temperature sensors are distributed at different heights of the reactor, so that comprehensive temperature data can be obtained in real time, reducing the impact of local temperature deviations. By calculating the average value of multiple temperature measurements, the overall temperature in the reactor can be obtained, ensuring the accuracy of temperature detection in the reactor.

[0075] In one embodiment, the temperature control is divided into a temperature rising stage and a constant temperature stage; step S102 includes:

[0076] Step 1: During the constant temperature stage, obtain the viscosity change data of the material during the target period, and calculate its average value and standard deviation.

[0077] Step 2: Calculate the absolute difference between the average value and the target viscosity.

[0078] Step three, using ultrasonic sensors at different locations, measure the propagation speed of ultrasonic waves in different areas, and calculate the standard deviation of multiple propagation speeds.

[0079] Step 4: if the absolute difference is less than the first threshold, the standard deviation of the viscosity is less than the second threshold, and the standard deviation of the propagation speed is less than the third threshold, then the melting and stirring is terminated to obtain the first glue solution.

[0080] In one implementation, the target time period is a period of time before the current moment, for example, nearly 1 minute. The viscosity and stability over a period of time are used to determine whether the current moment is completely reacted and mixed evenly. Errors at a single measurement point are avoided. The first threshold, the second threshold, and the third threshold can be determined by a technician based on historical data, for example, set to 20 mPa·s, 5 mPa·s, and 5 m / s, respectively.

[0081] In one implementation, a time point can be set, and when the constant temperature control of the reactor is started, the automatic detection will start at this time point. For example, the shortest completion time can be obtained through historical data. Pushing the shortest completion time forward for a period of time (for example, 20 minutes) and starting the detection from this time point can save the consumption of computing resources.

[0082] In one implementation, by obtaining viscosity change data during the constant temperature stage and calculating the average value and standard deviation, the mixing state and reaction process of the materials can be effectively monitored to ensure that the materials react fully during the stirring process and achieve the ideal uniformity and quality requirements, thereby avoiding uneven and low-quality glue.

[0083] In one implementation, the physical properties of the glue in different areas are evaluated by combining the measurement of distributed ultrasonic propagation velocity, which can more comprehensively evaluate the mixing uniformity of the materials. This multi-dimensional judgment method improves the control accuracy and reduces the error that may be caused by a single indicator.

[0084] In one embodiment, obtaining viscosity change data of a material within a target period includes:

[0085] Step 1: Obtain the liquid level in the reactor at the target sampling time, and obtain the immersion depth of the agitator based on the liquid level.

[0086] Step 2: Obtain the material temperature in the reactor.

[0087] Step 3: Obtain the torque of the stirrer.

[0088] Step 4: Use the immersion depth, material temperature and torque as inputs of the pre-trained viscosity prediction model to obtain the material viscosity at the target sampling time.

[0089] Step 5: Obtain the viscosity change data of the material according to multiple sampling moments within the target period.

[0090] The target sampling time is any sampling time within the target time period.

[0091] In one implementation, the viscosity prediction model is one of a multi-layer perceptron regression model, a support vector regression model, and a random forest regression model. Data with viscosity annotations are obtained through experiments, and supervised learning is performed to obtain a viscosity prediction model. By using multiple parameters as inputs to the viscosity prediction model, automated monitoring and control in the production process is achieved. This automated monitoring method reduces manual intervention, reduces human errors, and improves the reliability and stability of the production process.

[0092] The embodiment of the present invention provides a hot melt adhesive production control system. Figure 2 , Figure 2 This is a diagram of the architecture of a hot melt adhesive production control system provided by an embodiment of the present invention. The system includes:

[0093] The raw material conveying module is used to convey the materials to the reactor according to the preset formula.

[0094] The melting reaction module is used to melt and stir the materials and perform automatic detection to obtain a uniformly mixed first glue solution.

[0095] The impurity filtering module is used to filter the first glue solution to obtain the second glue solution.

[0096] The extrusion molding module is used to convey the second adhesive liquid to the extruder for extrusion molding to obtain the adhesive strip.

[0097] The finished product cutting module is used to cool and cut the rubber strips to obtain the target glue sticks.

[0098] A hot melt adhesive production control method provided in an embodiment of the present invention introduces automated detection technology for real-time monitoring and uniformity detection to ensure that the material achieves an ideal mixing effect during the melting stage, avoids excessive or insufficient stirring, shortens the mixing process time, and thus improves production efficiency.

[0099] In one embodiment, a plurality of temperature sensors are disposed at different heights in the reactor; a liquid level sensor is built into the reactor;

[0100] The melting reaction module includes a temperature control module, and the temperature control module includes:

[0101] The liquid level determination module is used to obtain the liquid level height in the reactor through the liquid level sensor.

[0102] The multi-point temperature acquisition module is used to obtain the temperature measurement values ​​of multiple temperature sensors under the liquid surface.

[0103] The temperature value determination module is used to take the average value of multiple temperature measurement values ​​as the real-time temperature in the reactor.

[0104] The automatic adjustment module is used to control the temperature of the material in the reactor according to the preset temperature control algorithm and the real-time temperature.

[0105] In one embodiment, the temperature control is divided into a heating stage and a constant temperature stage; the melting reaction module also includes a quality standard module; the quality standard module includes:

[0106] The delayed data acquisition module is used to obtain the viscosity change data of the material within the target period during the constant temperature stage, and calculate its average value and standard deviation.

[0107] The difference calculation module is used to calculate the absolute difference between the average value and the target viscosity.

[0108] The multi-point physical property detection module is used to measure the propagation speed of ultrasonic waves in different areas through ultrasonic sensors at different positions, and calculate the standard deviation of multiple propagation speeds.

[0109] The process control module is used to terminate the melting and stirring to obtain the first glue solution if the absolute difference is less than the first threshold, the standard deviation of the viscosity is less than the second threshold, and the standard deviation of the propagation speed is less than the third threshold.

[0110] In one embodiment, the delay data acquisition module includes:

[0111] The immersion depth detection module is used to obtain the liquid level in the reactor at the target sampling time, and obtain the immersion depth of the agitator according to the liquid level; the target sampling time is any sampling time within the target time period.

[0112] The temperature data acquisition module is used to obtain the material temperature in the reactor.

[0113] The torque data acquisition module is used to obtain the torque of the stirrer.

[0114] The viscosity prediction module is used to use the immersion depth, material temperature and torque as inputs of the pre-trained viscosity prediction model to obtain the material viscosity at the target sampling moment.

[0115] The time period data integration module is used to obtain the material viscosity change data according to the material viscosity at multiple sampling moments within the target time period.

[0116] In one embodiment, the viscosity prediction model is a multi-layer perceptron regression model, a support vector regression model, or a random forest regression model.

[0117] The above is a detailed description of an embodiment of the present invention, but the content is only a preferred embodiment of the present invention and cannot be considered to limit the scope of implementation of the present invention. All equivalent changes and improvements made within the scope of the present invention should still fall within the scope of the patent coverage of the present invention.

Claims

1. A hot melt adhesive production control method, characterized in that: The method comprises: According to the preset formula, the materials are transported to the reactor; The materials are melted and stirred, and automated testing is performed simultaneously to obtain a uniformly mixed first glue solution; filtering the first glue solution to obtain a second glue solution; The second adhesive liquid is conveyed to an extruder for extrusion molding to obtain an adhesive strip; The glue strip is cooled and cut to obtain a target glue stick.

2. A hot melt adhesive production control method according to claim 1, characterized in that: A plurality of temperature sensors are disposed at different heights in the reactor; a liquid level sensor is built into the reactor; While the material is being melted and stirred, temperature control is performed, and the temperature control includes: Obtaining the liquid level in the reactor through the liquid level sensor; Obtain temperature measurement values ​​of multiple temperature sensors below the liquid surface; The average value of the multiple temperature measurement values ​​is used as the real-time temperature in the reactor; The temperature of the material in the reactor is controlled according to a preset temperature control algorithm and the real-time temperature.

3. A hot melt adhesive production control method according to claim 2, characterized in that: The temperature control is divided into a heating stage and a constant temperature stage; the material is melted and stirred, and automatic detection is performed at the same time to obtain a uniformly mixed first glue solution, which includes: In the constant temperature stage, obtain the viscosity change data of the material within the target period, and calculate its average value and standard deviation; Calculating the absolute difference between the average value and the target viscosity; The ultrasonic sensors at different positions are used to measure the propagation speed of ultrasonic waves in different areas, and the standard deviation of multiple propagation speeds is calculated; If the absolute difference is smaller than the first threshold, the standard deviation of the viscosity is smaller than the second threshold, and the standard deviation of the propagation speed is smaller than the third threshold, the melting and stirring is terminated to obtain the first glue solution.

4. A hot melt adhesive production control method according to claim 3, characterized in that: The method of obtaining the viscosity change data of the material within the target period includes: For the target sampling time, the liquid level in the reactor is obtained, and the immersion depth of the stirrer is obtained according to the liquid level; the target sampling time is any sampling time within the target time period; Obtain the material temperature in the reactor; Get the torque of the stirrer; The immersion depth, material temperature and torque are used as inputs of a pre-trained viscosity prediction model to obtain the material viscosity at a target sampling time; According to multiple sampling moments within the target period, the viscosity change data of the material is obtained.

5. A hot melt adhesive production control method according to claim 4, characterized in that: The viscosity prediction model is one of a multi-layer perceptron regression model, a support vector regression model and a random forest regression model.

6. A hot melt adhesive production control system, characterized in that: The system comprises: The raw material conveying module is used to convey the materials to the reactor according to the preset formula; The melting reaction module is used to melt and stir the materials and perform automatic detection to obtain a uniformly mixed first glue solution; An impurity filtering module, used for filtering the first glue solution to obtain a second glue solution; An extrusion molding module, used for conveying the second adhesive liquid to an extruder for extrusion molding to obtain an adhesive strip; The finished product cutting module is used to cool and cut the glue strip to obtain the target glue stick.

7. A hot melt adhesive production control system according to claim 6, characterized in that: A plurality of temperature sensors are disposed at different heights in the reactor; a liquid level sensor is built into the reactor; The melting reaction module includes a temperature control module, and the temperature control module includes: A liquid level determination module, used to obtain the liquid level in the reactor through the liquid level sensor; A multi-point temperature acquisition module is used to obtain temperature measurement values ​​of multiple temperature sensors under the liquid surface; A temperature value determination module is used to use the average value of multiple temperature measurement values ​​as the real-time temperature in the reactor; The automatic adjustment module is used to control the temperature of the material in the reactor according to a preset temperature control algorithm and the real-time temperature.

8. A hot melt adhesive production control system according to claim 7, characterized in that: The temperature control is divided into a heating stage and a constant temperature stage; the melting reaction module also includes a quality standard module; the quality standard module includes: The delayed data acquisition module is used to obtain the viscosity change data of the material within the target period during the constant temperature stage, and calculate its average value and standard deviation; A difference calculation module, used for calculating the absolute difference between the average value and the target viscosity; The multi-point physical property detection module is used to measure the propagation speed of ultrasonic waves in different areas through ultrasonic sensors at different positions, and calculate the standard deviation of multiple propagation speeds; The process control module is used to terminate the melting and stirring to obtain the first glue solution if the absolute difference is less than a first threshold, the standard deviation of the viscosity is less than a second threshold, and the standard deviation of the propagation speed is less than a third threshold.

9. A hot melt adhesive production control system according to claim 8, characterized in that: The delay data acquisition module comprises: An immersion depth detection module is used to obtain the liquid level in the reactor at a target sampling time, and obtain the immersion depth of the agitator according to the liquid level; the target sampling time is any sampling time within the target time period; A temperature data acquisition module is used to obtain the material temperature in the reactor; A torque data acquisition module, used to acquire the torque of the stirrer; A viscosity prediction module, used to use the immersion depth, material temperature and torque as inputs of a pre-trained viscosity prediction model to obtain the material viscosity at a target sampling time; The time period data integration module is used to obtain the material viscosity change data according to the material viscosity at multiple sampling moments within the target time period.

10. A hot melt adhesive production control system according to claim 9, characterized in that: The viscosity prediction model is a multi-layer perceptron regression model, a support vector regression model or a random forest regression model.

Images