A temperature monitoring method and system for forging

Abstract

The present invention relates to the field of temperature monitoring, and in particular to a temperature monitoring method and system for forgings. The method comprises: obtaining temperature data at different times during forging, constructing a temperature sequence using the temperature data at different times, and calculating the degree of isolation of each temperature data; classifying the temperature sequence to obtain multiple sub-temperature sequences, calculating a variation index for each sub-temperature sequence, where the variation index represents the volatility of the sub-temperature sequence; and using the data in the sub-temperature sequence whose variation index is greater than a preset index threshold as the temperature data of the oxide scale. The present invention can distinguish the temperature data to obtain the temperature data of the oxide scale and the temperature data of the forging surface.

Description

Technical Field

[0001] The present invention relates to the field of temperature monitoring, and in particular to a temperature monitoring method and system for forging. Background Art

[0002] The temperature during the forging process directly affects the plasticity and fluidity of the metal material. If the temperature is too low, the material may become brittle, leading to cracks or failure to achieve the desired shape during forging. If the temperature is too high, the metal may oversoften, affecting the forming quality. Precise temperature control helps to control the metal's microstructure, ensuring that the mechanical properties and microstructure of the forging meet the design requirements. Excessively high or low temperatures may lead to grain coarsening or other undesirable structures, affecting the final mechanical properties. Therefore, when analyzing the forging quality of forgings, it is necessary to refer to the temperature data during the forging process to optimize the processing technology.

[0003] Zhang Yucun, "A Temperature Measurement Method for Hot Forgings Containing Oxide Scale Based on Infrared Spectroscopy," School of Electrical Engineering, Yanshan University, 2012. This paper, based on laboratory research on hot workpieces covered with thick oxide scale, proposes a unique infrared temperature measurement method. This method directly measures the temperature and emissivity of the oxide scale surface and then derives the true temperature of the forging's inner surface from the heat exchange between the oxide scale, the forging, and the external environment. This method overcomes the problem of temperature measurement errors caused by oxide scale coverage in conventional infrared thermometers. Finally, the feasibility of the method was verified through experiments.

[0004] During the forging process, the temperature of the forging is measured using a temperature measuring instrument. Since oxide scale forms on the forging surface during forging, and the temperature of the oxide scale is usually lower than the surface temperature of the forging, when measuring the surface temperature of the forging, if oxide scale is present on the forging surface, the measured temperature data will be the temperature of the oxide scale, not the surface temperature of the forging. As a result, the measured temperature data will contain part of the forging surface temperature data and part of the oxide scale temperature data, which is not conducive to analyzing the forging quality. Summary of the Invention

[0005] In order to solve the problem that the measured temperature data contains temperature data of oxide scale, which makes it inconvenient to analyze the forging quality, the present invention provides a temperature monitoring method and system for forging.

[0006] In a first aspect, the present invention provides a method for monitoring temperature during forging, which employs the following technical solution:

[0007] Obtain temperature data at different times during forging, construct a temperature sequence using the temperature data at different times, calculate the absolute value of the difference between each temperature data and the adjacent temperature data in the temperature sequence, and calculate the degree of isolation of each temperature data. The degree of isolation is positively correlated with the absolute value of the difference;

[0008] The temperature sequence is classified to obtain multiple sub-temperature sequences, and the variation index of each sub-temperature sequence is calculated. The variation index represents the volatility of the sub-temperature sequence; the data in the sub-temperature sequence whose variation index is greater than a preset index threshold is used as the temperature data of the oxide scale.

[0009] By monitoring the temperature during forging, the temperature data is obtained, and then the temperature data is differentiated to obtain the temperature data of the oxide scale and the temperature data of the forging surface, which facilitates the differentiation of the temperature data and improves the forging process.

[0010] Preferably, the expression of isolation degree is:

[0011]

[0012] Where, Indicates the degree of isolation of the temperature data at the i-th moment, represents the temperature data at the i-th moment, represents the temperature data at the i-1th moment, Indicates the temperature data at the i+1th moment.

[0013] By calculating the degree of isolation of temperature data, we can gain a preliminary understanding of the differences between temperature data and adjacent temperature data, providing a theoretical basis for determining the category to which the temperature data belongs.

[0014] Preferably, the method further includes calculating the variation factor of each sub-temperature sequence, and the calculation method is: fitting the data points in the sub-temperature sequence to obtain a fitting curve, calculating the absolute value of the slope of each data point, and normalizing the slope, and further calculating the absolute value mean of the slope of the data points in the sub-temperature sequence and the absolute value variance of the slope; and taking the ratio of the product of the absolute value variance and the absolute value mean to the number of data points as the variation factor of the sub-temperature sequence.

[0015] Based on the different volatility characteristics of the temperature data of the oxide scale and the temperature data of the forging surface, the variation factor is calculated from multiple dimensions, so that the variation factor can reflect the volatility of the sub-temperature series and facilitate the distinction of the sub-temperature series.

[0016] Preferably, the variation index calculation method is as follows: calculating the isolation degree of each temperature data, sorting the obtained multiple isolation degrees in descending order to obtain an isolation degree sequence, intercepting the first multiple data in the isolation degree sequence, and calculating the mean of the intercepted data; the expression of the variation index is:

[0017]

[0018] Where, represents the change index of the nth sub-temperature series, Represents the preset weight coefficient, represents the change factor of the nth sub-temperature series, Represents the mean of the truncated data in the isolation degree series.

[0019] By calculating the variation index of the sub-temperature sequences, we can understand the differences between adjacent sub-temperature sequences, which facilitates the classification of the sub-temperature sequences.

[0020] Preferably, the least square method is used to fit the data points in the sub-temperature series to obtain a fitting curve.

[0021] Preferably, the weight coefficient is calculated by constructing the objective function :

[0022]

[0023] Where, 、 、 They represent the change index of the n-1th, nth, and n+1th sub-temperature sequences respectively, and the maximum value of the objective function is solved to obtain the value of the weight coefficient.

[0024] Preferably, a swarm intelligence algorithm is used to solve the maximum value of the objective function.

[0025] By constructing the objective function to obtain the weight coefficient, the accuracy of the change index calculation results is improved, so that the change characteristics of the data points in the sub-temperature series can be accurately measured through the change index.

[0026] Preferably, the method further comprises the step of converting the temperature data of the oxide scale to obtain the temperature data of the forging surface.

[0027] Preferably, the method for classifying the temperature sequence to obtain multiple sub-temperature sequences is: using the optimal segmentation method to perform ordered sample clustering on the temperature sequence to obtain multiple clusters, and taking the temperature data in each cluster as a sub-temperature sequence.

[0028] In a second aspect, the present invention provides a temperature monitoring system for forgings, which adopts the following technical solution:

[0029] A temperature monitoring system for forgings includes a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, the temperature monitoring method for forgings described above is implemented.

[0030] The above-mentioned temperature monitoring method for forging is generated into a computer program and stored in a memory so as to be loaded and executed by a processor. Thus, a system is made based on the memory and the processor for easy use.

[0031] The present invention has the following technical effects:

[0032] The present invention obtains temperature data by monitoring the temperature during forging, and then distinguishes the temperature data to obtain temperature data of the oxide scale and temperature data of the forging surface, which facilitates the distinction of the temperature data and improves the forging process. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 The present invention is a flow chart of a temperature monitoring method for forging. DETAILED DESCRIPTION

[0034] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work shall fall within the scope of protection of the present invention.

[0035] The embodiment of the present invention discloses a temperature monitoring method for forging a forging, referring to Figure 1 , including the following steps, as follows:

[0036] S1: Obtain temperature data at different times during forging.

[0037] Infrared sensors are used to collect temperature data of forgings in real time during forging. The sampling frequency is once every 2 seconds. The collected temperature data is the temperature data of the forging surface or the temperature data of the oxide scale. The temperature data obtained at different times are used to construct a temperature sequence.

[0038] S2: Calculate the degree of isolation of each temperature data in the temperature series.

[0039] The expression of isolation degree is:

[0040]

[0041] Where, Indicates the degree of isolation of the temperature data at the i-th moment, represents the temperature data at the i-th moment, represents the temperature data at the i-1th moment, Indicates the temperature data at the i+1th moment.

[0042] Oxide scale is a corrosion product formed when steel undergoes oxidation at high temperatures during the forging process. It usually adheres to the surface of the forging. Its adhesion time is mainly affected by the impact of the forging press. Therefore, its adhesion time may be one sampling moment or multiple sampling moments.

[0043] Because the iron reacts with oxygen to release heat at the moment the oxide scale is generated, the temperature of the oxide scale is higher than the temperature of the forging surface. Subsequently, the heat dissipation rate of the oxide scale is greater than the heat dissipation rate of the forging surface, causing the subsequent temperature of the oxide scale to be lower than the temperature of the forging surface. Therefore, during the forging process, if there is oxide scale on the forging surface at the i-th moment, and there is no oxide scale on the forging surface at the i-1st and i+1st moments, the temperature collected is the forging surface temperature. At this time, the isolation degree of the temperature data at the i-th moment is greater than the isolation degree of the i-1st and i+1st moments. It can be understood that if the isolation degree at the i-th moment is greater than the isolation degree of the i-1st and i+1st moments at the same time, and the temperature data at the i-th moment is greater than the temperature data at the i-1st and i+1st moments, then the temperature data obtained at the i-th moment is the temperature data of the forging surface. In this case, the temperature data at the i-th moment is recorded as the marked temperature.

[0044] S3: Divide the temperature sequence into multiple sub-temperature sequences.

[0045] If the oxide scale adheres to the forging surface for a long time, the multiple continuous temperature data collected during the adhesion period will all be the temperature data of the oxide scale surface. Therefore, it is necessary to filter the temperature data of the multiple oxide scales in the temperature sequence. It should be noted that when the oxide scale adheres to the forging surface for a long time, the temperature of the oxide scale surface will show a trend of first rising briefly and then decreasing overall.

[0046] In the temperature sequence, the mean of the temperature data on both sides of the marked temperature is calculated and inserted into the temperature sequence instead of the marked temperature to reduce the influence of the marked temperature on the sub-temperature sequence. Similarly, the mean of the temperature data on both sides of the noise data point is calculated and inserted into the temperature sequence instead of the marked temperature to reduce the influence of the noise data point on the sub-temperature sequence. The temperature sequence is clustered using the optimal partitioning method to obtain multiple clusters, and the temperature data in each cluster is regarded as a sub-temperature sequence.

[0047] S4: Calculate the change factor of each sub-temperature series.

[0048] The data points in the sub-temperature series are fitted using the least squares method to obtain a fitting curve. The absolute value of the slope of each data point is calculated, and the slope is normalized using the Min-Max normalization algorithm. The absolute mean and absolute variance of the slopes of the data points in the sub-temperature series are further calculated. The ratio of the product of the absolute variance and the absolute mean to the number of data points is used as the change factor of the sub-temperature series.

[0049] The expression of the change factor is:

[0050]

[0051] Where, represents the change factor of the nth sub-temperature series, represents the absolute mean of the slopes of the data points in the nth sub-temperature series, represents the absolute value variance of the slope of the data point in the nth sub-temperature series, Indicates the number of data points in the nth sub-temperature series.

[0052] During the forging process, both the forging and the oxide scale are exposed to air simultaneously. The temperature change rate of the forging is slower than that of the oxide scale—in other words, faster than the temperature drop rate of the forging. Therefore, a larger mean absolute slope value further reflects that the data in the corresponding sub-temperature series is the temperature data of the oxide scale. Conversely, a smaller mean absolute slope value further reflects that the data in the corresponding sub-temperature series is the temperature data of the forging surface. Furthermore, due to the oxide scale's small mass and rapid heat dissipation, the oxide scale temperature data is highly volatile, resulting in a larger variance in the absolute slope values of the data points in the corresponding sub-sequence. However, the temperature data of the forging surface is less volatile, resulting in a smaller variance in the absolute slope values of the data points in the corresponding sub-sequence. During forging, the forging is subjected to external forces, which shortens the time from the formation of the oxide scale to its detachment, thus resulting in a shorter sub-sequence length.

[0053] In summary, when the variation factor of a subsequence is large, it can be preliminarily indicated that the data points in the corresponding subsequence are the temperature data of the oxide scale, otherwise, they are the temperature data of the forging surface.

[0054] S5: Calculate the variation index of each sub-temperature series.

[0055] S51: For each sub-temperature sequence, calculate the degree of isolation of each temperature data, use the Min-Max normalization algorithm to normalize the isolation degree, sort the multiple isolation degrees after processing in descending order to obtain an isolation degree sequence, intercept the first multiple data in the isolation degree sequence, and calculate the mean of the intercepted data.

[0056] The expression of the change index is:

[0057]

[0058] Where, represents the change index of the nth sub-temperature series, Indicates the preset weight coefficient, the value range is (0,1), represents the change factor of the nth sub-temperature series, It represents the mean of the data intercepted in the isolation degree sequence. For example, the first three data in the isolation degree sequence are intercepted and the mean of the three data is calculated.

[0059] During the forging process, the temperature data of the oxide scale shows a process of first rising briefly and then falling rapidly. Therefore, if the data in the sub-temperature series is the temperature data of the oxide scale, the isolation degree series corresponding to the sub-temperature series is that the first few data are larger as a whole, and the last few data are smaller as a whole. The mean of the intercepted data is If the data in the sub-temperature series is the temperature data of the forging surface, the isolation degree series corresponding to the sub-temperature series is relatively stable as a whole, and the mean of the intercepted data is Therefore, when the variation index is large, it further indicates that the data point in the corresponding subsequence is the temperature data of the oxide scale, otherwise, it is the temperature data of the forging surface.

[0060] S52: Calculate the weight coefficient.

[0061] Constructing the objective function , the expression is:

[0062]

[0063] Where, 、 、 Represents the change index of the n-1th, nth, and n+1th sub-temperature sequences. A swarm intelligence algorithm is used to solve for the maximum value of the objective function, and the value of the weight coefficient at the maximum value is used as the final value of the weight coefficient. The objective function represents the overall difference between the change index of a sub-temperature sequence and adjacent sub-temperature sequences. Solving for the maximum value of the objective function is to amplify the difference between the change index of the sub-temperature sequences, making it easier to distinguish the temperature data of the oxide scale from the temperature data of the forging surface.

[0064] Exemplarily, the maximum value of the objective function is solved using a particle swarm optimization algorithm, wherein the number of particles is 50, the maximum number of iterations is 100, the inertia weight is 0.7, and the acceleration constant is 2.0.

[0065] S6: Convert the temperature data of the oxide scale to obtain the temperature data of the forging surface.

[0066] When the change index of the sub-temperature sequence is greater than the preset index threshold, it indicates that the data points in the sub-temperature sequence have large fluctuations, which is consistent with the temperature data change characteristics of the oxide scale. Therefore, the data in the sub-temperature sequence with a change index greater than the preset index threshold is used as the temperature data of the oxide scale, and the rest is the temperature data of the forging surface. The index threshold is selected artificially according to the actual situation. For example, the index threshold is 0.3.

[0067] After obtaining the temperature data of the oxide scale, the temperature data of the oxide scale is converted to obtain the temperature data of the forging surface, which is used for analyzing the forging quality and forging process of the forging.

[0068] The expression is: , where Indicates the temperature data of the forging surface at the ath moment, Indicates the temperature data of the oxide scale at the ath moment, The temperature conversion function represents the temperature conversion function and the conversion of the temperature data of the oxide scale to obtain the temperature data of the forging surface is the existing technology. For details, please refer to the documents cited in the background technology. The calculation process will not be repeated here.

[0069] An embodiment of the present invention further discloses a temperature monitoring system for forgings, comprising a processor and a memory, wherein the memory stores computer program instructions. When the computer program instructions are executed by the processor, a temperature monitoring method for forgings according to the present invention is implemented.

[0070] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface. The configuration and functions of these components are known in the art and will not be described in detail here.

[0071] The above are all preferred embodiments of the present invention, and are not intended to limit the scope of protection of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the scope of protection of the present invention.

Claims

1. A temperature monitoring method for forging, characterized in that: Including steps: The temperature data at different times during forging are obtained, and a temperature sequence is constructed using the temperature data at different times. The absolute value of the difference between each temperature data and the adjacent temperature data in the temperature sequence is calculated, and the degree of isolation of each temperature data is calculated. The expression for the degree of isolation is: Where, Indicates the degree of isolation of the temperature data at the i-th moment, represents the temperature data at the i-th moment, represents the temperature data at the i-1th moment, Represents the temperature data at the i+1th moment; the degree of isolation is positively correlated with the absolute value of the difference; Calculate the change factor of each sub-temperature series by fitting the data points in the sub-temperature series to obtain a fitting curve, calculate the absolute value of the slope of each data point, normalize the slope, and further calculate the absolute mean and absolute variance of the slopes of the data points in the sub-temperature series. The ratio of the product of the absolute variance and the absolute mean to the number of data points is used as the change factor of the sub-temperature series. The temperature series is classified into multiple sub-temperature series, and the change index of each sub-temperature series is calculated. The change index calculation method is as follows: the isolation degree of each temperature data is calculated, the multiple isolation degrees are sorted from large to small to obtain an isolation degree series, the first multiple data in the isolation degree series are intercepted, and the mean of the intercepted data is calculated; the expression of the change index is: Where, represents the change index of the nth sub-temperature series, Represents the preset weight coefficient, represents the change factor of the nth sub-temperature series, Indicates the mean of the intercepted data in the isolation degree series; The variation index represents the volatility of the sub-temperature sequence; the data in the sub-temperature sequence whose variation index is greater than a preset index threshold is used as the temperature data of the oxide scale.

2. A temperature monitoring method for forging according to claim 1, characterized in that: The least squares method is used to fit the data points in the sub-temperature series to obtain the fitting curve.

3. The temperature monitoring method for forging according to claim 1, characterized in that: The calculation method of weight coefficient is: construct objective function : Where, 、 、 They represent the change index of the n-1th, nth, and n+1th sub-temperature sequences respectively, and the maximum value of the objective function is solved to obtain the value of the weight coefficient.

4. A temperature monitoring method for forging according to claim 3, characterized in that: The swarm intelligence algorithm is used to solve the maximum value of the objective function.

5. The temperature monitoring method for forging according to claim 1, characterized in that: The method also includes the step of converting the temperature data of the oxide scale to obtain the temperature data of the forging surface.

6. A temperature monitoring method for forging according to claim 1, characterized in that: The method for classifying the temperature sequence to obtain multiple sub-temperature sequences is as follows: using the optimal segmentation method to perform ordered sample clustering on the temperature sequence to obtain multiple clusters, and treating the temperature data in each cluster as a sub-temperature sequence.

7. A temperature monitoring system for forging, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a temperature monitoring method for forging according to any one of claims 1 to 6 is implemented.

Images