Intelligent temperature monitoring method for tire production molding machine

Abstract

The present invention relates to the technical field of temperature monitoring, and in particular to a method for intelligently monitoring the temperature of a tire production molding machine. The method quantifies the corresponding temperature influence according to the fluctuation of reference values ​​of various temperature influence parameters, and screens out the temperature influence interference moments that have an influence on the temperature according to the temperature influence; then, according to the temperature mutation of the molding machine after each temperature influence interference moment, the temperature mutation response moment when the temperature influence occurs is determined; and the temperature influence degree of the temperature is determined in combination with the time series correlation between the reference value at the temperature influence moment and the molding machine temperature at the temperature mutation response moment; finally, the molding machine temperature is adjusted in real time according to the obtained temperature influence degree, and a more accurate real temperature corresponding to the current moment is determined, so that the abnormal temperature monitored according to the real temperature is more accurate, so that the effect of abnormal temperature monitoring of the tire production molding machine is better.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature monitoring, and in particular to a method for intelligently monitoring the temperature of a tire production molding machine. Background Art

[0002] The tire molding machine is a key equipment in the tire manufacturing process. It combines various components together through a heat bonding process, and the bonding quality is directly affected by temperature. The appropriate molding machine temperature can have enough heat to make the rubber molecules diffuse and fuse with each other, making the produced tires higher in quality; while abnormal molding machine temperature will destroy the rubber, resulting in poor quality tires; therefore, it is necessary to monitor the temperature of the molding machine used in tire production in real time and issue early warnings for abnormal molding machine temperatures in time to ensure tire production quality.

[0003] The existing technology usually uses temperature measuring equipment such as temperature sensors or infrared temperature sensors to monitor the temperature of the tire bonding of the molding machine in real time, so as to set the temperature threshold according to the monitored molding machine temperature to monitor abnormal temperature and issue an early warning when abnormal temperature is detected. However, the equipment and materials have a certain thermal inertia, and there may be a lag in the response of temperature to changes in the pressure of the roller and the speed of the roller. For example, when the speed of the roller increases suddenly, the temperature will not change immediately, but it will take a certain amount of time to reach a new equilibrium state. After the temperature rise is detected, it also takes time to control the machine to stop. At this time, the rubber may have been damaged, thereby affecting the quality of the tire. As a result, the accuracy of the early warning based on the abnormal temperature monitored by the set temperature threshold by the existing technology is low, making the effect of abnormal temperature monitoring of the molding machine used in tire production poor. Summary of the invention

[0004] The present application provides a method for intelligent monitoring the temperature of a molding machine for tire production. The method first quantifies the temperature influence corresponding to each temperature influence parameter at each sampling moment according to the fluctuation of the reference value of various temperature influence parameters, and screens out the temperature influence interference moments that have an impact on the temperature according to the temperature influence; then, according to the temperature mutation of the molding machine after each temperature influence interference moment, determines the temperature mutation response moment when the response temperature influence occurs; and combines the time series correlation between the reference value at the temperature influence moment and the molding machine temperature at the temperature mutation response moment to determine the temperature influence degree of the molding machine temperature; finally, according to the obtained temperature influence degree, the molding machine temperature in the current processing process of the tire molding machine is adjusted in real time to determine a more accurate real temperature corresponding to the current moment, so that the abnormal temperature monitored according to the real temperature is more accurate, which solves the problem of low accuracy of early warning of abnormal temperature monitored only according to the set temperature threshold with the help of the prior art, and makes the temperature abnormality monitoring effect of the molding machine for tire production better.

[0005] The present application provides a method for intelligently monitoring the temperature of a tire molding machine for tire production, comprising:

[0006] During each historical processing of the tire building machine, the building machine temperature and reference values ​​of each temperature influencing parameter at each sampling moment are obtained; the types of temperature influencing parameters include roller pressure and roller speed;

[0007] In each historical processing process, the possibility of a sudden change of each temperature influencing parameter at each sampling moment is determined according to the fluctuation of the reference value of each temperature influencing parameter in the time sequence neighborhood of each sampling moment; and the parameter sudden change moment of each temperature influencing parameter is screened out according to the sudden change possibility;

[0008] Determine the degree of temperature influence interference at each parameter mutation moment under each temperature influence parameter according to the fluctuation of reference values ​​of other types of temperature influence parameters in the time sequence neighborhood at each parameter mutation moment of each temperature influence parameter in each historical processing process; and select the temperature influence moment of each temperature influence parameter according to the degree of temperature influence interference;

[0009] According to the temperature mutation of the molding machine after the temperature influence moment, the temperature mutation response moment at each temperature influence moment under each temperature influence parameter is determined; in all historical processing processes, according to the time series correlation between the reference value of each temperature influence moment of each temperature influence parameter and the molding machine temperature at each corresponding temperature mutation response moment, the temperature influence degree of each temperature influence parameter is determined;

[0010] According to the temperature influence degree, the molding machine temperature at the current moment in the current processing of the tire molding machine is adjusted to determine the real temperature at the current moment; and the molding machine temperature abnormality monitoring for tire production is performed according to the real temperature.

[0011] Furthermore, the process of obtaining the mutation possibility includes:

[0012] In the time sequence, the difference between the reference value of each temperature influence parameter at each sampling moment and the reference value at the previous sampling moment is used as the reference change value of each temperature influence parameter at each sampling moment; in the time sequence, all sampling moments within the preset first time neighborhood window of each sampling moment are used as the neighborhood moments of each sampling moment;

[0013] In each historical processing process, the variance of the reference values ​​of each temperature influence parameter at all neighboring moments corresponding to each sampling moment is taken as the discrete degree of the neighboring reference quantity corresponding to each temperature influence parameter at each sampling moment; the mean of the reference change values ​​of each temperature influence parameter at all neighboring moments corresponding to each sampling moment is taken as the fluctuation degree of the neighboring reference quantity corresponding to each temperature influence parameter at each sampling moment;

[0014] The product of the discrete degree of the neighborhood reference quantity and the fluctuation degree of the neighborhood reference quantity is normalized to determine the possibility of mutation of each temperature influencing parameter at each sampling moment.

[0015] Furthermore, the process of obtaining the parameter mutation moment includes:

[0016] The sampling moment when the mutation probability is greater than the preset mutation threshold is taken as the parameter mutation moment of each temperature-affecting parameter in each historical processing process.

[0017] Furthermore, the process of obtaining the degree of interference affected by temperature includes:

[0018] Another temperature influence parameter corresponding to each temperature influence parameter is used as a comparison influence parameter of each temperature influence parameter;

[0019] At all sampling moments within the preset second time neighborhood window at each parameter mutation moment of each temperature influencing parameter in each historical processing process, the normalized value of the variance of all reference numerical values ​​corresponding to the comparison influencing parameter is used as the degree of temperature influence interference at each parameter mutation moment under each temperature influencing parameter.

[0020] Furthermore, the process of obtaining the temperature impact moment includes:

[0021] In each historical processing process, the parameter mutation moment when the temperature influence interference degree corresponding to each temperature influence parameter is less than the preset interference threshold is taken as the temperature influence moment of each temperature influence parameter in each historical processing process.

[0022] Furthermore, the process of acquiring the temperature mutation response time includes:

[0023] The difference between the molding machine temperature at each sampling moment and the molding machine temperature at the previous sampling moment is used as the reference temperature change value at each sampling moment; among the preset first number of sampling moments after each temperature influence moment under each temperature influence parameter, the sampling moment corresponding to the first reference temperature change value greater than the preset temperature change threshold in the time sequence is used as the temperature mutation response moment at each temperature influence moment under each temperature influence parameter.

[0024] Furthermore, the process of obtaining the temperature influence degree includes:

[0025] Under each temperature influence parameter, the average of the reference temperature change values ​​at the preset second number of sampling moments after each corresponding temperature mutation response moment is used as the temperature change characteristic value at each temperature mutation response moment;

[0026] Under each temperature influence parameter, the difference between the reference value at each temperature influence moment and the reference value at the next sampling moment is used as the parameter change characteristic value at each temperature influence moment under each temperature influence parameter;

[0027] In each historical processing process, after arranging the reference change characteristic values ​​of all temperature influence moments under each temperature influence parameter in time sequence, the reference change characteristic value sequence of each temperature influence parameter is determined; after arranging the temperature change characteristic values ​​of all temperature mutation response moments under each temperature influence parameter in time sequence, the temperature change characteristic value sequence of each temperature influence parameter is determined;

[0028] The Pearson correlation coefficient between the reference change characteristic value sequence and the temperature change characteristic value sequence is used as the reference temperature correlation of each temperature influencing parameter in each historical processing process; the average value of the reference temperature correlation of all historical processing processes under each temperature influencing parameter is used as the temperature influence degree of each temperature influencing parameter.

[0029] Furthermore, the process of obtaining the real temperature includes:

[0030] Determine a weighted reference change value of each temperature influence parameter at the current moment according to a change in the reference value of each temperature influence parameter at the current moment and the temperature influence degree;

[0031] The accumulated value of the weighted reference change values ​​of all types of temperature influencing parameters at the current moment is used as the temperature adjustment weight at the current moment;

[0032] The positive correlation mapping value of the temperature adjustment weight and the molding machine temperature at the current moment are taken as the real temperature at the current moment.

[0033] Furthermore, the process of obtaining the weighted reference change value includes:

[0034] Under each temperature influence parameter, the difference between the reference value at the current moment and the reference value at the previous sampling moment is used as the real-time value change value at the current moment; the product of the temperature influence degree of each temperature influence parameter and the real-time value change value is used as the weighted reference change value of each temperature influence parameter at the current moment.

[0035] Furthermore, the process of monitoring the temperature anomaly of the tire production molding machine according to the real temperature includes:

[0036] When the actual temperature is less than or equal to the preset temperature threshold, it is determined that the temperature of the tire production molding machine at the current moment is normal;

[0037] When the actual temperature is greater than the preset temperature threshold, it is determined that the temperature of the tire production molding machine at the current moment is abnormal.

[0038] This application has the following beneficial effects:

[0039] The tire thermal bonding process heats the tire core and the tire body using the heating device of the molding machine to make the rubber material reach a suitable viscosity state. While heating, a certain pressure of the roller is applied by the rolling device, and the roller rotates to tightly fit the components together. The change in the bonding temperature of the tire of the molding machine is caused by the change in the pressure of the roller and the speed of the roller. As the pressure between the roller and the tire body increases, the layers between the tires are more closely bonded, resulting in enhanced thermal conductivity of the tire and increased bonding temperature of the tire of the molding machine; in addition, when the roller speed is faster during the tire bonding process, the contact frequency between the roller and the tire body and between the tire and the bonding equipment increases, and the higher roller speed will also increase the relative sliding speed of the friction surface, further aggravating the effect of frictional heat generation; therefore, this application uses the pressure of the roller and the roller speed as two temperature influencing parameters that affect the temperature of the molding machine.

[0040] The change of the pressure of the roller and the speed of the roller will cause the temperature change of the bonding part of the molding machine, and the temperature of the molding machine will have an upward trend only after the pressure of the roller and the speed of the roller change suddenly for a period of time; therefore, only based on the real-time measured temperature of the molding machine, it is usually impossible to monitor the abnormality of the molding machine. For the current moment, if the corresponding pressure of the roller and the speed of the roller are large at the current moment, the measured molding machine temperature cannot respond to the abnormality caused by the change of the pressure of the roller and the speed of the roller in time, resulting in the low accuracy of directly using the molding machine temperature to monitor the abnormal temperature of the molding machine for tire production. Therefore, it is necessary to adjust the real-time molding machine temperature according to the real-time pressure change of the roller and the speed of the roller; however, it is necessary to consider that the reference value change of different temperature-affecting parameters has different influences on the temperature change, so this application needs to analyze the influence of each temperature-affecting parameter on the temperature of the molding machine, so as to make more accurate real-time abnormal monitoring temperature adjustment. Therefore, this application analyzes the temperature changes caused by the changes of the temperature-affecting parameters in the historical processing process to indirectly analyze the degree of temperature influence. First, according to the reference value change of each temperature-affecting parameter in the time series, the parameter mutation moment of the mutation is determined.

[0041] Then it is necessary to consider that in some time periods, multiple temperature influencing parameters will jointly affect the temperature of the molding machine. Therefore, in order to more accurately quantify the impact of each temperature influencing parameter on the temperature of the molding machine, this application screens out the temperature influence moment when each temperature influencing parameter dominates the temperature influence based on the reference value fluctuations of other types of temperature influencing parameters in the time neighborhood of each parameter mutation moment of each temperature influencing parameter in each historical processing process.

[0042] And according to the response of the molding machine temperature to the parameter change after each temperature influence moment, the temperature mutation response moment when the temperature is affected and changed is determined; thereby, the temperature influence degree of each temperature influence parameter is quantified according to the timing correlation between the reference value of each temperature influence moment of each temperature influence parameter and the molding machine temperature at each corresponding temperature mutation response moment; finally, according to the obtained temperature influence degree, the molding machine temperature in the current processing process of the tire molding machine is adjusted in real time to determine a more accurate real temperature corresponding to the current moment, so that the abnormal temperature monitored according to the real temperature is more accurate, which solves the problem of low accuracy of early warning based on abnormal temperature monitored only according to the set temperature threshold with the help of existing technology, and makes the temperature abnormality monitoring effect of molding machines used in tire production better. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0044] Figure 1 A flow chart of a method for intelligently monitoring the temperature of a tire molding machine provided in one embodiment of the present invention. DETAILED DESCRIPTION

[0045] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the specific implementation method, structure, characteristics and effects of a temperature intelligent monitoring method for a tire production molding machine proposed by the present invention are described in detail below in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" does not necessarily refer to the same embodiment, and the specific features, structures or characteristics in one or more embodiments may be combined in any suitable form. In addition, the terms "first" and "second" are used for descriptive purposes only and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of technical features indicated. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features.

[0046] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0047] The specific scheme of the intelligent temperature monitoring method of a tire production molding machine provided by the present invention is described in detail below with reference to the accompanying drawings.

[0048] The present application embodiment provides a method for intelligently monitoring the temperature of a tire molding machine for tire production. Figure 1 , which shows a flow chart of a method for intelligently monitoring the temperature of a tire production molding machine provided by an embodiment of the present invention, the method comprising:

[0049] Step S101: in each historical processing of the tire building machine, obtaining the building machine temperature and reference values ​​of each temperature influencing parameter at each sampling moment; the types of temperature influencing parameters include roller pressure and roller speed.

[0050] The tire thermal bonding process heats the tire core and the tire body using the heating device of the molding machine to make the rubber material reach a suitable viscosity state. While heating, a certain pressure of the roller is applied by the rolling device, and the roller rotates to tightly fit the components together. The change in the bonding temperature of the tire of the molding machine is caused by the change in the pressure of the roller and the speed of the roller. As the pressure between the roller and the tire body increases, the layers between the tires are more closely bonded, resulting in enhanced thermal conductivity of the tire and increased bonding temperature of the tire of the molding machine; in addition, when the roller speed is faster during the tire bonding process, the contact frequency between the roller and the tire body and between the tire and the bonding equipment increases, and the higher roller speed will also increase the relative sliding speed of the friction surface, further aggravating the effect of frictional heat generation; therefore, this application uses the pressure of the roller and the roller speed as two temperature influencing parameters that affect the temperature of the molding machine.

[0051] In a specific implementation of an embodiment of the present invention, during each historical processing of the tire forming machine, the forming machine temperature at each sampling moment is measured in a non-contact manner by means of an infrared temperature sensor. The infrared temperature sensor is installed at a distance of 0.5m between the tire and the tire and close to the direction of the fitting part of the tire core and the tire body, so that the fitting part of the tire of the forming machine can be monitored more accurately; and at the same time, the pressure between the pressure wheel and the tire body is measured by means of a pressure sensor, that is, the reference value of the pressure wheel pressure at each sampling moment; and the roller speed value is measured by means of a speed sensor, that is, the reference value of the roller speed at each sampling moment. It should be noted that in the embodiment of the present invention, the time interval between two adjacent sampling moments is set to 1 second, and the total number of historical processing processes is set to 30 times, that is, 30 historical processing processes before the current moment, which can be adjusted according to the specific implementation environment.

[0052] Step S102: In each historical processing process, the possibility of a mutation of each temperature influencing parameter at each sampling moment is determined according to the fluctuation of the reference value of each temperature influencing parameter in the time sequence neighborhood of each sampling moment; and the parameter mutation moment of each temperature influencing parameter is selected according to the mutation possibility.

[0053] The changes in the pressure of the roller and the speed of the roller will cause the temperature change of the bonding part of the molding machine, and the temperature of the molding machine will tend to rise only after the pressure of the roller and the speed of the roller change suddenly for a period of time; therefore, it is usually impossible to monitor the abnormality of the molding machine based on the real-time measured temperature of the molding machine. For the current moment, if the corresponding pressure of the roller and the speed of the roller are large at the current moment, the measured molding machine temperature cannot respond to the abnormality caused by the change of the pressure of the roller and the speed of the roller in time, resulting in the low accuracy of directly using the molding machine temperature to monitor the abnormal temperature of the molding machine for tire production. Therefore, it is necessary to adjust the real-time molding machine temperature according to the real-time pressure change of the roller and the speed of the roller; however, it is necessary to consider that the reference value change of different temperature-affecting parameters has different influences on the temperature change, so this application needs to analyze the temperature influence of each temperature-affecting parameter on the molding machine temperature, so as to make more accurate real-time abnormal monitoring temperature adjustment. Therefore, this application analyzes the temperature changes caused by the changes of the temperature-affecting parameters in the historical processing process to indirectly analyze the degree of temperature influence. Firstly, according to the reference value change of each temperature-affecting parameter in time series, the mutation possibility of each sampling moment is determined, so as to screen out the parameter mutation moment when the parameter mutation occurs according to the mutation possibility.

[0054] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the possibility of mutation includes:

[0055] In time sequence, the difference between the reference value of each temperature influencing parameter at each sampling moment and the reference value at the previous sampling moment is used as the reference change value of each temperature influencing parameter at each sampling moment; in time sequence, all sampling moments within the preset first time neighborhood window of each sampling moment are used as the neighborhood moments of each sampling moment. In a specific implementation of an embodiment of the present invention, a time window containing 9 sampling moments centered on each sampling moment is used as the preset first time neighborhood window of each sampling moment, which can be adjusted according to the specific implementation environment. The larger the reference change value, the greater the change in the corresponding temperature influencing parameter at the corresponding sampling moment, and the more likely it is to cause temperature change.

[0056] In each historical processing process, the variance of the reference values ​​of each temperature influence parameter at all neighborhood moments corresponding to each sampling moment is taken as the discrete degree of the neighborhood reference quantity corresponding to each temperature influence parameter at each sampling moment; the mean of the reference change values ​​of each temperature influence parameter at all neighborhood moments corresponding to each sampling moment is taken as the fluctuation degree of the neighborhood reference quantity corresponding to each temperature influence parameter at each sampling moment. The variance can characterize the discrete degree of a set of data. The larger the variance, the more chaotic the corresponding data distribution; therefore, the larger the discrete degree of the neighborhood reference quantity, the more obvious the fluctuation of the reference value at the corresponding sampling moment, and the more likely the parameter mutation will occur. The reference change value characterizes the instantaneous parameter change at each sampling moment. Therefore, for each sampling moment, the larger the overall reference change value of all the corresponding neighborhood moments, the more obvious the fluctuation of the reference value in the temporal sequence of the sampling moment, and the greater the possibility of the corresponding reference value mutation.

[0057] Therefore, according to the characteristic that the greater the discreteness of the neighborhood reference quantity and the greater the fluctuation of the neighborhood reference quantity, the greater the possibility that the corresponding temperature influence parameter will mutate at the corresponding sampling moment, the product of the discreteness of the neighborhood reference quantity and the fluctuation of the neighborhood reference quantity is normalized to determine the possibility of mutation of each temperature influence parameter at each sampling moment.

[0058] In a specific implementation of the embodiment of the present invention, the process of obtaining the mutation possibility is expressed by the formula: ;in, For the The first The temperature influence parameter is The possibility of mutation at each sampling moment; For the The first The number of neighboring moments corresponding to each sampling moment; For the The first The temperature influence parameter is The sampling time corresponds to the Reference values ​​at neighboring moments; For the The first The temperature influence parameter is The sampling time corresponds to the Reference values ​​at neighboring moments; is the absolute value symbol; For the The first The temperature influence parameter is The sampling time corresponds to the Reference change value at each neighborhood moment; For the The first The temperature influence parameter is The degree of fluctuation of the reference quantity of the neighborhood corresponding to each sampling moment; For the The first The temperature influence parameter is The discrete degree of the neighborhood reference quantity corresponding to the sampling time, that is, The first The temperature influence parameter is The variance of the reference values ​​at all neighboring moments corresponding to the sampling moment; It is a linear normalization function. The implementer can adjust the normalization method according to the specific implementation environment.

[0059] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the parameter mutation moment includes:

[0060] The sampling moment when the mutation probability is greater than the preset mutation threshold is used as the parameter mutation moment of each temperature-affecting parameter in each historical processing process; when the mutation probability is greater, the reference value fluctuation of the corresponding temperature-affecting parameter at the corresponding sampling moment is more obvious, and the possibility of affecting the temperature is greater, so the parameter mutation moment that characterizes the effect on temperature change in this application is screened out by the preset mutation threshold. In a specific implementation of an embodiment of the present invention, the preset mutation threshold is set to 0.7, which can be adjusted according to the specific implementation environment.

[0061] Step S103: Determine the degree of temperature influence interference at each parameter mutation moment under each temperature influence parameter according to the fluctuation of reference values ​​of other types of temperature influence parameters in the time series neighborhood at each parameter mutation moment of each temperature influence parameter in each historical processing process; and select the temperature influence moment of each temperature influence parameter according to the degree of temperature influence interference.

[0062] Then it is necessary to consider that in some time periods, multiple temperature influencing parameters will jointly affect the temperature of the molding machine. Therefore, in order to more accurately quantify the impact of each temperature influencing parameter on the temperature of the molding machine, this application determines the degree of temperature influence interference at each parameter mutation moment under each temperature influencing parameter based on the reference value fluctuations of other types of temperature influencing parameters in the time neighborhood of each parameter mutation moment of each temperature influencing parameter in each historical processing process, and screens out the temperature influence moment when each temperature influencing parameter dominates the temperature influence according to the degree of temperature influence interference.

[0063] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the degree of temperature influence interference includes: taking another temperature influence parameter corresponding to each temperature influence parameter as a comparison influence parameter of each temperature influence parameter; taking the normalized value of the variance of all reference values ​​corresponding to the comparison influence parameter at all sampling moments within the preset second time neighborhood window at each parameter mutation moment of each temperature influence parameter in each historical processing process as the degree of temperature influence interference at each parameter mutation moment of each temperature influence parameter. For each parameter mutation moment of each temperature influence parameter, if the variance of the reference value corresponding to the comparison influence parameter at all sampling moments within the corresponding preset second time neighborhood window is small, it means that in the time sequence neighborhood of the corresponding parameter mutation moment, the change of another temperature influence parameter is not obvious, that is, the influence of another temperature influence parameter on temperature change is small, which indirectly means that the influence of the corresponding temperature influence parameter on temperature at the reference mutation moment is small. For example, for any parameter mutation moment corresponding to the roller pressure, if the variance of all reference values ​​corresponding to the roller speed in the preset second time neighborhood window of the corresponding reference mutation moment is small, it means that at the reference mutation moment, the temperature change caused by the roller pressure is less affected by the roller speed. In a specific implementation of the embodiment of the present invention, a time window containing 9 sampling moments centered on each parameter mutation moment is used as the preset second time neighborhood window of each parameter mutation moment, which can be adjusted according to the specific implementation environment.

[0064] In a specific implementation of the embodiment of the present invention, the process of obtaining the degree of interference affected by temperature is expressed by the formula: ;in, For the The first The temperature influence parameter is The degree of interference caused by temperature at the moment of parameter mutation; For the The first The temperature influence parameter is The variance of all reference values ​​in the corresponding comparison-affecting parameter at all sampling moments within the preset second time neighborhood window at the moment of parameter mutation; It is a linear normalization function. The implementer can adjust the normalization method according to the specific implementation environment.

[0065] Preferably, in some possible implementations of the embodiments of the present invention, the process of acquiring the temperature impact moment includes:

[0066] In each historical processing process, the temperature influence interference degree corresponding to each temperature influence parameter is less than the parameter mutation moment corresponding to the preset interference threshold value, which is used as the temperature influence moment of each temperature influence parameter in each historical processing process. If the relationship between each temperature influence parameter and temperature is to be accurately analyzed, it is necessary to ensure that other temperature influence parameters will not affect the temperature change or have a small impact on the temperature change while each temperature influence parameter affects the temperature change, so as to more accurately quantify the impact of each temperature influence parameter on the temperature change; therefore, for each parameter mutation moment at which each temperature influence parameter affects the temperature, the smaller the corresponding temperature influence interference degree is, the smaller the impact of other types of temperature influence parameters on the temperature change in the neighborhood of the corresponding reference mutation moment is, and the more accurate the temperature impact represented by the reference mutation moment is; therefore, by setting the preset interference threshold value, the parameter mutation moment with a small temperature influence interference degree is selected as the temperature influence moment of each temperature influence parameter in each historical processing process, that is, at the temperature influence moment, the impact of the corresponding temperature influence parameter on the temperature change can be accurately analyzed. In a specific implementation of an embodiment of the present invention, the preset interference threshold value is set to 0.3, which can be adjusted according to the specific implementation environment.

[0067] Step S104: Determine the temperature mutation response moment at each temperature influence moment under each temperature influence parameter according to the temperature mutation of the molding machine after the temperature influence moment; in all historical processing processes, determine the temperature influence degree of each temperature influence parameter according to the timing correlation between the reference value of each temperature influence moment of each temperature influence parameter and the corresponding molding machine temperature at each temperature mutation response moment.

[0068] After determining the temperature influence moment at which each temperature influence parameter dominates the temperature influence, the temperature mutation response moment at which the temperature is affected and changed is further determined based on the response of the molding machine temperature to the parameter change after each temperature influence moment; thereby, the temperature influence degree of each temperature influence parameter is quantified based on the timing correlation between the reference value of each temperature influence moment of each temperature influence parameter and the corresponding molding machine temperature at each temperature mutation response moment.

[0069] Preferably, in some possible implementations of the embodiments of the present invention, the process of acquiring the temperature mutation response time includes:

[0070] The difference between the molding machine temperature at each sampling moment and the molding machine temperature at the previous sampling moment is used as the reference temperature change value at each sampling moment; in the preset first number of sampling moments after each temperature influence moment under each temperature influence parameter, the sampling moment corresponding to the first reference temperature change value greater than the preset temperature change threshold in the time sequence is used as the temperature mutation response moment for each temperature influence moment under each temperature influence parameter. In a specific implementation of an embodiment of the present invention, the preset first number is set to 120, which can be adjusted according to the specific implementation environment. It should be noted that when there is no reference temperature change value greater than the preset temperature change threshold in the preset first number of sampling moments after each temperature influence moment under each temperature influence parameter, the sampling moment corresponding to the largest reference temperature change value is used as the temperature mutation response moment for each temperature influence moment under each temperature influence parameter, which will not be further elaborated here.

[0071] Firstly, each temperature influence moment of each temperature influence parameter will have an influence on the temperature, and the temperature change caused by the influence is usually delayed. Therefore, after taking the temperature change greater than the preset temperature change threshold as the characteristic of the temperature change, the sampling moment corresponding to the first reference temperature change value greater than the preset temperature change threshold after each temperature influence moment is taken as the temperature mutation response moment corresponding to each temperature influence moment, that is, the temperature change at each temperature mutation response moment is caused by the change of the temperature influence parameter corresponding to the corresponding temperature influence moment. Further, according to the correlation between the temperature change and the reference value change of the corresponding temperature influence parameter type, the temperature influence degree of each temperature influence parameter is quantified.

[0072] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the temperature influence degree includes:

[0073] Under each temperature influence parameter, the average of the reference temperature change values ​​at the preset second number of sampling moments after each corresponding temperature mutation response moment is used as the temperature change characteristic value at each temperature mutation response moment. In a specific implementation of the embodiment of the present invention, the preset second number is set to 5; by calculating the temperature change characteristic value, the temperature change characteristics within the time series neighborhood of each temperature mutation response moment can be combined, so as to improve the accuracy of the temperature response to a certain extent, and improve the robustness of the subsequent analysis, and reduce the impact of chance.

[0074] Under each temperature influencing parameter, the difference between the reference value at each temperature influencing moment and the reference value at the next sampling moment is used as the parameter change characteristic value at each temperature influencing moment under each temperature influencing parameter. The larger the reference change characteristic value, the greater the reference value change of the corresponding temperature influencing parameter at the corresponding temperature influencing moment, and the greater the impact on the temperature. If the correlation between the corresponding temperature influencing parameter and the temperature is large, then the larger the corresponding reference change characteristic value, the larger the temperature change characteristic value at the corresponding temperature mutation response moment will be due to the correlation; therefore, the correlation between each reference change characteristic value and the corresponding temperature change characteristic value in the time series can be used to characterize the correlation between each temperature influencing parameter and the temperature, that is, the degree of influence of each temperature influencing parameter on the temperature.

[0075] Therefore, in each historical processing, after arranging the reference change characteristic values ​​of all temperature influence moments under each temperature influence parameter in time order, the reference change characteristic value sequence of each temperature influence parameter is determined; after arranging the temperature change characteristic values ​​of all temperature mutation response moments under each temperature influence parameter in time order, the temperature change characteristic value sequence of each temperature influence parameter is determined; the Pearson correlation coefficient between the reference change characteristic value sequence and the temperature change characteristic value sequence is used as the reference temperature correlation of each temperature influence parameter in each historical processing. The greater the reference temperature correlation, the greater the correlation between the temperature influence parameter and the temperature in the corresponding historical processing, that is, the greater the influence of the temperature influence parameter on the temperature. Further combined with all historical processing processes, the degree of influence of each temperature influence parameter on the temperature is comprehensively characterized, and the mean value of the reference temperature correlation of all historical processing processes under each temperature influence parameter is used as the temperature influence degree of each temperature influence parameter. For each temperature influence parameter, the greater the overall reference temperature correlation reflected in all historical processing processes, the greater the overall influence degree of the corresponding temperature influence parameter on the temperature.

[0076] In a specific implementation of the embodiment of the present invention, the process of obtaining the temperature influence degree is expressed by the formula: ;in, For the The degree of temperature influence of the temperature-influencing parameters; is the total number of historical processing processes; For the The first The reference temperature correlation of the temperature-affecting parameter, i.e. The first The Pearson correlation coefficient between the reference change characteristic value sequence of the temperature influence parameter and the temperature change characteristic value sequence. It should be noted that the Pearson correlation coefficient is a technical means well known to those skilled in the art and will not be further described here.

[0077] Step S105: adjusting the molding machine temperature at the current moment in the current processing of the tire molding machine according to the degree of temperature influence, determining the actual temperature at the current moment; and monitoring the temperature abnormality of the molding machine for tire production according to the actual temperature.

[0078] Finally, the molding machine temperature in the current processing of the tire molding machine is adjusted in real time according to the obtained temperature influence degree, and a more accurate real temperature corresponding to the current moment is determined, so that the abnormal temperature monitored according to the real temperature is more accurate, which solves the problem of low accuracy of early warning based on abnormal temperature monitored only according to the set temperature threshold by using the existing technology, and makes the temperature abnormality monitoring of the molding machine used in tire production better.

[0079] Preferably, in some possible implementations of the embodiments of the present invention, the process of obtaining the real temperature includes:

[0080] According to the reference value change of each temperature influence parameter at the current moment and the degree of temperature influence, the weighted reference change value of each temperature influence parameter at the current moment is determined. The degree of temperature influence reflects the influence of the change of each temperature influence parameter on the temperature change, so it is necessary to combine the real-time temperature influence parameter change to determine the temperature change weight at the current moment. Preferably, in some possible implementation methods of the embodiments of the present invention, the process of obtaining the weighted reference change value includes:

[0081] Under each temperature influencing parameter, the difference between the reference value at the current moment and the reference value at the previous sampling moment is taken as the real-time value change value at the current moment; the product between the temperature influence degree of each temperature influencing parameter and the real-time value change value is taken as the weighted reference change value of each temperature influencing parameter at the current moment. The real-time value change value represents the instantaneous change of the reference value of each temperature influencing parameter at the current moment, and the temperature influence degree represents the influence of the real-time change of each temperature influencing parameter on the temperature change. Therefore, the specific influence of each temperature influencing parameter on the temperature at the current moment is further determined according to the product between the temperature influence degree of each temperature influencing parameter and the real-time value change value, that is, the weighted reference change value.

[0082] Since the temperature is affected by all temperature influencing parameters, in order to more accurately adjust the temperature at the current moment, the accumulated value of the weighted reference change values ​​of all types of temperature influencing parameters at the current moment is used as the temperature adjustment weight at the current moment. In a specific implementation of an embodiment of the present invention, the process of obtaining the temperature adjustment weight is expressed by the formula: ;in, For the current moment The temperature adjustment weight of is the number of types of temperature-affected parameters; For the The degree of temperature influence of the temperature-influencing parameters; For the The current moment under the temperature influence parameters Reference value of For the The current moment under the temperature influence parameters The reference value of the previous sampling moment; It is an absolute value symbol. It should be noted that if there is no previous sampling moment at the current moment, the corresponding temperature adjustment weight is set to 0; is the absolute value symbol; For the The current moment under the temperature influence parameters Real-time numerical change value; For the current moment Next The weighted reference change value of the temperature-affecting parameter.

[0083] Further, the real-time temperature adjustment is performed according to the temperature adjustment weight, and the positive correlation mapping value of the temperature adjustment weight and the molding machine temperature at the current moment are used as the real temperature at the current moment. In a specific implementation of the embodiment of the present invention, the process of obtaining the real temperature is expressed by the formula: ;in, For the current moment The real temperature; For the current moment The molding machine temperature; For the current moment The temperature adjustment weight of It is a linear normalization function. The implementer can adjust the normalization method according to the specific implementation environment. For the current moment The temperature adjustment weights are positively correlated with the mapping values.

[0084] Preferably, in some possible implementations of the embodiments of the present invention, the process of monitoring the temperature abnormality of the tire production molding machine according to the real temperature includes:

[0085] When the actual temperature is less than or equal to the preset temperature threshold, the temperature of the tire production molding machine at the current moment is determined to be normal; when the actual temperature is greater than the preset temperature threshold, the temperature of the tire production molding machine at the current moment is determined to be abnormal. When the actual temperature is greater than the preset temperature threshold, it means that the temperature of the molding machine is high. At this time, the rubber of the tire may be deformed, thereby affecting the quality of the tire. Therefore, it is determined that the temperature of the tire production molding machine at the current moment is normal, and an alarm is issued to stop the tire processing of the molding machine, and remind the staff to inspect the machine. When the actual temperature is less than or equal to the preset temperature threshold, it means that the temperature of the molding machine is normal. In a specific implementation of an embodiment of the present invention, the preset temperature threshold is set to 150 degrees Celsius, which can be adjusted according to the specific implementation environment.

[0086] In summary, a method for intelligent monitoring temperature of a molding machine for tire production quantifies the temperature influence corresponding to each temperature influence parameter at each sampling moment according to the fluctuation of the reference value of various temperature influence parameters, and screens out the temperature influence interference moments that have an impact on the temperature according to the temperature influence; then, according to the temperature mutation of the molding machine after each temperature influence interference moment, the temperature mutation response moment when the response temperature influence occurs is determined; and the degree of temperature influence on the molding machine temperature is determined by combining the time series correlation between the reference value at the temperature influence moment and the molding machine temperature at the temperature mutation response moment; finally, according to the obtained temperature influence degree, the molding machine temperature in the current processing process of the tire molding machine is adjusted in real time to determine a more accurate real temperature corresponding to the current moment, so that the abnormal temperature monitored according to the real temperature is more accurate, which solves the problem of low accuracy of early warning based on the abnormal temperature monitored only according to the set temperature threshold with the help of the existing technology, and makes the temperature abnormality monitoring of the molding machine for tire production better.

[0087] It should be noted that the sequence of the above embodiments of the present invention is only for description and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the accompanying drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0088] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

Claims

1. A method for intelligently monitoring the temperature of a tire molding machine for production, characterized in that: The method comprises: During each historical processing of the tire building machine, the building machine temperature and reference values ​​of each temperature influencing parameter at each sampling moment are obtained; the types of temperature influencing parameters include roller pressure and roller speed; In each historical processing process, the possibility of a sudden change of each temperature influencing parameter at each sampling moment is determined according to the fluctuation of the reference value of each temperature influencing parameter in the time sequence neighborhood of each sampling moment; and the parameter sudden change moment of each temperature influencing parameter is screened out according to the sudden change possibility; Determine the degree of temperature influence interference at each parameter mutation moment under each temperature influence parameter according to the fluctuation of reference values ​​of other types of temperature influence parameters in the time sequence neighborhood at each parameter mutation moment of each temperature influence parameter in each historical processing process; and select the temperature influence moment of each temperature influence parameter according to the degree of temperature influence interference; According to the temperature mutation of the molding machine after the temperature influence moment, the temperature mutation response moment at each temperature influence moment under each temperature influence parameter is determined; in all historical processing processes, according to the time series correlation between the reference value of each temperature influence moment of each temperature influence parameter and the molding machine temperature at each corresponding temperature mutation response moment, the temperature influence degree of each temperature influence parameter is determined; According to the temperature influence degree, the molding machine temperature at the current moment in the current processing of the tire molding machine is adjusted to determine the real temperature at the current moment; and the molding machine temperature abnormality monitoring for tire production is performed according to the real temperature.

2. The method for intelligently monitoring the temperature of a tire molding machine according to claim 1, characterized in that: The process of obtaining the mutation possibility includes: In the time sequence, the difference between the reference value of each temperature influence parameter at each sampling moment and the reference value at the previous sampling moment is used as the reference change value of each temperature influence parameter at each sampling moment; in the time sequence, all sampling moments within the preset first time neighborhood window of each sampling moment are used as the neighborhood moments of each sampling moment; In each historical processing process, the variance of the reference values ​​of each temperature influence parameter at all neighboring moments corresponding to each sampling moment is taken as the discrete degree of the neighboring reference quantity corresponding to each temperature influence parameter at each sampling moment; the mean of the reference change values ​​of each temperature influence parameter at all neighboring moments corresponding to each sampling moment is taken as the fluctuation degree of the neighboring reference quantity corresponding to each temperature influence parameter at each sampling moment; The product of the discrete degree of the neighborhood reference quantity and the fluctuation degree of the neighborhood reference quantity is normalized to determine the possibility of mutation of each temperature influencing parameter at each sampling moment.

3. The method for intelligently monitoring the temperature of a tire molding machine according to claim 1, characterized in that: The process of obtaining the parameter mutation moment includes: The sampling moment when the mutation probability is greater than the preset mutation threshold is taken as the parameter mutation moment of each temperature-affecting parameter in each historical processing process.

4. The method for intelligently monitoring the temperature of a tire molding machine according to claim 1, characterized in that: The process of obtaining the degree of temperature interference includes: Another temperature influence parameter corresponding to each temperature influence parameter is used as a comparison influence parameter of each temperature influence parameter; At all sampling moments within the preset second time neighborhood window at each parameter mutation moment of each temperature influencing parameter in each historical processing process, the normalized value of the variance of all reference numerical values ​​corresponding to the comparison influencing parameter is used as the degree of temperature influence interference at each parameter mutation moment under each temperature influencing parameter.

5. The method for intelligently monitoring the temperature of a tire molding machine according to claim 1, characterized in that: The process of obtaining the temperature impact moment includes: In each historical processing process, the parameter mutation moment when the temperature influence interference degree corresponding to each temperature influence parameter is less than the preset interference threshold is taken as the temperature influence moment of each temperature influence parameter in each historical processing process.

6. The method for intelligently monitoring the temperature of a tire production molding machine according to claim 1, characterized in that: The process of obtaining the temperature mutation response time includes: The difference between the molding machine temperature at each sampling moment and the molding machine temperature at the previous sampling moment is used as the reference temperature change value at each sampling moment; among the preset first number of sampling moments after each temperature influence moment under each temperature influence parameter, the sampling moment corresponding to the first reference temperature change value greater than the preset temperature change threshold in the time sequence is used as the temperature mutation response moment at each temperature influence moment under each temperature influence parameter.

7. The method for intelligently monitoring the temperature of a tire molding machine according to claim 6, characterized in that: The process of obtaining the temperature influence degree includes: Under each temperature influence parameter, the average of the reference temperature change values ​​at the preset second number of sampling moments after each corresponding temperature mutation response moment is used as the temperature change characteristic value at each temperature mutation response moment; Under each temperature influence parameter, the difference between the reference value at each temperature influence moment and the reference value at the next sampling moment is used as the parameter change characteristic value at each temperature influence moment under each temperature influence parameter; In each historical processing process, after arranging the reference change characteristic values ​​of all temperature influence moments under each temperature influence parameter in time sequence, the reference change characteristic value sequence of each temperature influence parameter is determined; after arranging the temperature change characteristic values ​​of all temperature mutation response moments under each temperature influence parameter in time sequence, the temperature change characteristic value sequence of each temperature influence parameter is determined; The Pearson correlation coefficient between the reference change characteristic value sequence and the temperature change characteristic value sequence is used as the reference temperature correlation of each temperature influencing parameter in each historical processing process; the average value of the reference temperature correlation of all historical processing processes under each temperature influencing parameter is used as the temperature influence degree of each temperature influencing parameter.

8. The method for intelligently monitoring the temperature of a tire molding machine according to claim 1, characterized in that: The process of obtaining the real temperature includes: Determine a weighted reference change value of each temperature influence parameter at the current moment according to a change in the reference value of each temperature influence parameter at the current moment and the temperature influence degree; The accumulated value of the weighted reference change values ​​of all types of temperature influencing parameters at the current moment is used as the temperature adjustment weight at the current moment; The positive correlation mapping value of the temperature adjustment weight and the molding machine temperature at the current moment are taken as the real temperature at the current moment.

9. The method for intelligently monitoring the temperature of a tire molding machine according to claim 8, characterized in that: The process of obtaining the weighted reference change value includes: Under each temperature influence parameter, the difference between the reference value at the current moment and the reference value at the previous sampling moment is used as the real-time value change value at the current moment; the product of the temperature influence degree of each temperature influence parameter and the real-time value change value is used as the weighted reference change value of each temperature influence parameter at the current moment.

10. The method for intelligently monitoring the temperature of a tire molding machine according to claim 1, characterized in that: The process of monitoring the temperature abnormality of the tire production molding machine according to the real temperature includes: When the actual temperature is less than or equal to the preset temperature threshold, it is determined that the temperature of the tire production molding machine at the current moment is normal; When the actual temperature is greater than the preset temperature threshold, it is determined that the temperature of the tire production molding machine at the current moment is abnormal.

Images