Fuzzy PID (Proportion Integration Differentiation) control algorithm dynamic thermal assistance method based on time sequence

Abstract

The invention discloses a time sequence-based fuzzy PID (Proportion Integration Differentiation) control algorithm dynamic thermal assistance method, which comprises the following steps of: acquiring temperature data of a drilling and riveting area in real time through an infrared sensor, mapping temperature deviation and a change rate thereof to an adjustment weight of a PID parameter based on a fuzzy rule base, and solving the problem of parameter mismatch of the traditional PID in a nonlinear system. Process parameter database matching: establishing an association rule base of a material combination such as a metal-composite material and a preset temperature threshold value, and dynamically setting a temperature control target by combining a thermal physical property heat conductivity coefficient and a melting point of the material so as to realize differential regulation and control of dissimilar materials; the temperature-vibration coupling model based on the LSTM neural network is constructed to precisely and cooperatively regulate and control internal correlation of temperature and vibration, vibration disturbance brought in the temperature rising process is accurately obtained, and dynamic adjustment of the temperature and vibration in the drilling and riveting process is achieved by finely adjusting the power of the active damper.

Description

Technical Field

[0001] The invention relates to the technical field of automated processing and intelligent control, and in particular to a dynamic thermal assistance method of a fuzzy PID control algorithm based on a time series. Background Art

[0002] As a highly efficient process for connecting dissimilar materials, flow drilling and riveting technology is widely used in aerospace, automobile manufacturing and other fields. However, in the traditional flow drilling and riveting process, the accuracy of heat source temperature control directly affects the riveting quality and material properties. In the prior art, heat-assisted drilling and riveting mostly uses PID control algorithm to adjust the electromagnetic induction heating power, but there are the following problems: 1. Poor adaptability of temperature control: Traditional PID control parameters are fixed, which makes it difficult to cope with nonlinear and time-varying temperature fluctuations caused by factors such as material heat capacity differences and environmental heat loss during the drilling and riveting process. Overshoot or response lag is prone to occur, resulting in uneven rivet forming or thermal damage to the substrate, such as local ablation of composite materials.

[0003] 2. Insufficient compatibility of dissimilar materials: The thermal expansion coefficients of metals and composite materials are significantly different. Existing methods lack differentiated temperature control strategies for different material combinations, resulting in cross-sectional stress concentration and reduced riveting strength.

[0004] 3. High energy consumption and reliance on manual experience: The traditional process requires setting the heating power threshold through repeated trial and error, lacks a dynamic optimization mechanism based on real-time data, and cannot adaptively match process parameters, resulting in energy waste.

[0005] Furthermore, the flow drilling and riveting technology uses a rotating drill bit to penetrate the upper and lower plates and form a riveting hole, and then uses the plastic deformation of the carbon steel rivet under the action of mechanical force to tap and tighten between the two plates, and the screw head seats on the upper plate, thereby achieving the connection of dissimilar materials. However, during the high-speed and high-pressure drilling and riveting process, the dynamic coupling effect of temperature and vibration factors still has a significant impact on the process accuracy and material properties, which is specifically manifested in the following technical problems:

[0006] In the drilling and riveting process, the interaction between temperature and vibration directly affects the processing quality: Temperature influence: The instantaneous temperature of the friction between the carbon steel screw head and the plate can reach 300-500℃. Although the melting point of carbon steel rivets is greater than 1400℃ and they will not soften, high temperature will cause the problem of thermal stress concentration, which is specifically manifested in the thermal stress concentration when the plates are connected. Frictional heat generation at high speeds will inevitably lead to differences in the thermal expansion coefficients of metal substrates such as high-strength steel and carbon steel rivets, resulting in a peak interface residual stress of more than 150MPa.

[0007] The traditional process adopts a separate temperature and vibration control strategy, but does not solve the inherent correlation defects between the two: Single temperature control such as PID algorithm: Only by adjusting the heating power to compensate for the substrate temperature, but ignores the following problems: Vibration causes the infrared temperature sensor to offset by 0.5-1mm, and the temperature measurement error reaches ±15℃; Carbon steel rivets have a high thermal conductivity of 50W / m·K, and heat quickly diffuses to the substrate, aggravating thermal damage to the composite material; Fixed PID parameters cannot adapt to dynamic thermal load changes, such as friction heat power during drilling period>2kW, and only 0.8kW during riveting period, resulting in temperature overshoot>10% or response lag adjustment time>6s. Summary of the invention

[0008] In view of the technical problems in the prior art, the present invention provides a flow drilling and riveting heat-assisted method based on a fuzzy PID control algorithm, comprising the following steps: Step S1: collecting temperature data of the drilling and riveting processing area in real time; Step S2: comparing the temperature data with the current material combination temperature threshold value preset in the process parameter database, and calculating the temperature deviation value and its change rate; Step S3: Construct a fuzzy reasoning rule base, and dynamically adjust the PID parameters of the PID controller according to the temperature deviation value and its change rate based on the fuzzy rule base. The PID parameters include the proportional coefficient , integral coefficient and the differential coefficient ; Step S4: generating a control signal according to the adjusted PID parameters, adjusting the output power of the electromagnetic induction heating device, thereby dynamically controlling the temperature of the drilling and riveting processing area; In the heating process of step S4, a temperature-vibration coupling model based on an LSTM neural network is constructed, historical temperature data and historical vibration data are obtained, a heating sequence in the historical temperature data and a corresponding vibration sequence in the historical vibration data are obtained, and the cross-correlation is calculated to determine the effective time lag, and the heating sequence is used as input, and the vibration sequence after the effective time lag is used as a label, and the temperature-vibration coupling model is trained to obtain an optimized temperature-vibration coupling model; Importing the temperature rise sequence in step S4 into the temperature-vibration coupling model based on the LSTM neural network to obtain a predicted vibration rise sequence; dynamically adjusting the control force of the active damper according to the data of the vibration rise sequence; Step S5: Based on steps S1 to S4, the temperature and vibration of the drilling and riveting processing area are dynamically adjusted to obtain the riveting force curve in each drilling and riveting process, and the preset parameters of the fuzzy reasoning rule library are optimized by analyzing the stability of the riveting force curve.

[0009] Furthermore, the method for establishing the fuzzy reasoning rule base in step S3 is specifically as follows: The fuzzy set of temperature deviation value is defined as {negative large, negative small, zero, positive small, positive large}, and the fuzzy set of change rate is defined as {negative fast, negative slow, zero, positive slow, positive fast}; Construct a fuzzy rule table to map the temperature deviation value and its change rate to the adjustment weight of the PID parameters. The rule form is: If e is A and Δe is B, then Δ =C,Δ =D,Δ =E, where A and B are input fuzzy sets, and C, D, and E are output fuzzy sets; in, represents the temperature deviation value, Δe represents the rate of change of the temperature deviation value, Δ Indicates the change in the proportionality coefficient, Δ Indicates the change in the integral coefficient, Δ Indicates the change in the differential coefficient.

[0010] Furthermore, the process parameter database includes: Preset temperature thresholds for different material combinations; The material combination includes at least two types: metal-metal and metal-composite materials; Thermophysical parameters of each material, including thermal conductivity, melting point and maximum allowable heat-affected zone width; Mapping relationship table between historical riveting quality data and temperature control parameters.

[0011] Furthermore, in the process of dynamically adjusting the PID parameters in step S3: The adjustment weight of the proportional coefficient is positively correlated with the absolute value of the temperature deviation; The adjustment weight of the integral coefficient is negatively correlated with the absolute value of the rate of change of the temperature deviation value; The adjustment weight of the differential coefficient is positively correlated with the product of the temperature deviation value and the rate of change.

[0012] Furthermore, the power regulation of the electromagnetic induction heating device adopts PWM pulse width modulation technology, and the corresponding relationship between the power output and the PID control signal satisfies: ; in, is the heating power at time t, Indicates the temperature deviation value at time t.

[0013] Furthermore, the specific process of obtaining the temperature rise sequence in the historical temperature data and the corresponding vibration rise sequence in the historical vibration data, and calculating the cross-correlation to determine the effective time lag is as follows: Get the mutual correlation coefficient between the temperature rise sequence and the vibration rise sequence, expressed as: in, Indicates that the heating sequence and the vibration sequence are delayed in time The mutual correlation coefficient under The heating sequence is The temperature of the moment, The rising sequence is The amplitude of the moment, is the mean of the warming series, represents the mean of the rising vibration sequence, is the length of the time series, is the time lag, which indicates the number of delayed steps of the vibration-raising sequence relative to the heating sequence; Will The time lag corresponding to the preset threshold is taken as the effective time lag, that is, .

[0014] Furthermore, step S3 is specifically as follows: Fuzzification of input variables: Get temperature deviation value Determine the corresponding domain and use the triangular membership function to divide the corresponding fuzzy set into {negative large , negative small , zero , Zheng Xiao , Zhengda }; Get the rate of change of temperature deviation value Determine the corresponding domain, and use Gaussian membership function to divide the corresponding fuzzy set into {negative fast , negative slow ,zero , is slow , just fast }; Construct a fuzzy reasoning library based on the fuzzy reasoning table corresponding to the temperature deviation value and its change rate; Enter the real-time temperature deviation value and the rate of change of temperature deviation , based on the fuzzy reasoning library, obtain the corresponding fuzzy output of PID parameters; Defuzzification: The center of gravity method COG is used to convert the fuzzy output into accurate PID parameter adjustment, thereby completing the tuning of the PID parameters of the dynamic tuning PID controller.

[0015] Furthermore, the process flow of drilling and riveting includes drilling period, riveting period and tool withdrawal period in sequence. The change rate of temperature deviation value of the processing area during drilling period, riveting period and tool withdrawal period is Make sure the corresponding domains are different; Based on this, a process-oriented fuzzy rule base is constructed; Temperature deviation The corresponding domain is determined based on the melting point of the drilling and riveting material.

[0016] The positive and progressive effects of the present invention are:

[0017] 1) The temperature data of the drilling and riveting area is collected in real time through infrared sensors. The temperature deviation and its change rate are mapped to the adjustment weight of the PID parameters based on the fuzzy rule base to solve the parameter mismatch problem of traditional PID in nonlinear systems.

[0018] 2) Process parameter database matching: Establish an association rule library between material combinations such as metal-composite materials and preset temperature thresholds, dynamically set temperature control targets based on the thermal conductivity and melting point of the material's thermophysical properties, and achieve differentiated regulation of heterogeneous materials.

[0019] 3) The present invention constructs a temperature-vibration coupling model based on the LSTM neural network to precisely coordinate and control the intrinsic relationship between temperature and vibration, accurately obtain the vibration disturbance caused by the heating process, and realize dynamic adjustment of the temperature and vibration of the drilling and riveting process by fine-tuning the power of the active damper. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 The invention discloses a flow chart of the steps of a flow drilling and riveting heat-assisted method based on a fuzzy PID control algorithm. DETAILED DESCRIPTION

[0021] The following describes the embodiments of the present invention through specific examples, and those skilled in the art can easily understand other advantages and effects of the present invention from the contents disclosed in this specification. The present invention can also be implemented or applied through other different specific embodiments, and the details in this specification can also be modified or changed in various ways based on different viewpoints and applications without departing from the spirit of the present invention.

[0022] A flow drilling and riveting heat-assisted method based on fuzzy PID control algorithm comprises the following steps: Step S1: Real-time acquisition of temperature data of the drilling and riveting processing area; specifically, the temperature data acquisition and preprocessing uses an infrared temperature sensor to collect the temperature signal of the drilling and riveting area in real time, and the sampling frequency is set to 100 Hz; the original temperature data is processed by Kalman filtering to eliminate noise interference and ensure that the temperature error of the input controller is ≤±0.5°C; Step S2: comparing the temperature data with the current material combination temperature threshold value preset in the process parameter database, and calculating the temperature deviation value and its change rate; Step S3: Construct a fuzzy reasoning rule base, and dynamically adjust the PID parameters of the PID controller according to the temperature deviation value and its change rate based on the fuzzy rule base. The PID parameters include the proportional coefficient , integral coefficient and the differential coefficient ; Step S4: generating a control signal according to the adjusted PID parameters, adjusting the output power of the electromagnetic induction heating device, thereby dynamically controlling the temperature of the drilling and riveting processing area; In the heating process of step S4, a temperature-vibration coupling model based on an LSTM neural network is constructed, historical temperature data and historical vibration data are obtained, a heating sequence in the historical temperature data and a corresponding vibration sequence in the historical vibration data are obtained, and the cross-correlation is calculated to determine the effective time lag, and the heating sequence is used as input, and the vibration sequence after the effective time lag is used as a label, and the temperature-vibration coupling model is trained to obtain an optimized temperature-vibration coupling model; Importing the temperature rise sequence in step S4 into the temperature-vibration coupling model based on the LSTM neural network to obtain a predicted vibration rise sequence; dynamically adjusting the control force of the active damper according to the data of the vibration rise sequence; Step S5: Based on steps S1 to S4, the temperature and vibration of the drilling and riveting processing area are dynamically adjusted to obtain the riveting force curve in each drilling and riveting process, and the preset parameters of the fuzzy reasoning rule library are optimized by analyzing the stability of the riveting force curve.

[0023] Furthermore, the method for establishing the fuzzy reasoning rule base in step S3 is specifically as follows: The fuzzy set of temperature deviation value is defined as {negative large, negative small, zero, positive small, positive large}, and the fuzzy set of change rate is defined as {negative fast, negative slow, zero, positive slow, positive fast}; Construct a fuzzy rule table to map the temperature deviation value and its change rate to the adjustment weight of the PID parameters. The rule form is: If e is A and Δe is B, then Δ =C,Δ =D,Δ =E, where A and B are input fuzzy sets, and C, D, and E are output fuzzy sets; in, represents the temperature deviation value, Δe represents the rate of change of the temperature deviation value, Δ Indicates the change in the proportionality coefficient, Δ Indicates the change in the integral coefficient, Δ Indicates the change in the differential coefficient.

[0024] Furthermore, the process parameter database includes: Preset temperature thresholds for different material combinations; The material combination includes at least two types: metal-metal and metal-composite materials; Thermophysical parameters of each material, including thermal conductivity, melting point and maximum allowable heat-affected zone width; Mapping relationship table between historical riveting quality data and temperature control parameters.

[0025] Furthermore, in the process of dynamically adjusting the PID parameters in step S3: The adjustment weight of the proportional coefficient is positively correlated with the absolute value of the temperature deviation; The adjustment weight of the integral coefficient is negatively correlated with the absolute value of the rate of change of the temperature deviation value; The adjustment weight of the differential coefficient is positively correlated with the product of the temperature deviation value and the rate of change.

[0026] Furthermore, the power regulation of the electromagnetic induction heating device adopts PWM pulse width modulation technology, and the corresponding relationship between the power output and the PID control signal satisfies: ; in, is the heating power at time t, Indicates the temperature deviation value at time t.

[0027] Furthermore, the specific process of obtaining the temperature rise sequence in the historical temperature data and the corresponding vibration rise sequence in the historical vibration data, and calculating the cross-correlation to determine the effective time lag is as follows: Get the mutual correlation coefficient between the temperature rise sequence and the vibration rise sequence, expressed as: in, Indicates that the heating sequence and the vibration sequence are delayed in time The mutual correlation coefficient under The heating sequence is The temperature of the moment, The rising sequence is The amplitude of the moment, is the mean of the warming series, represents the mean of the rising vibration sequence, is the length of the time series, is the time lag, which indicates the number of delayed steps of the vibration-raising sequence relative to the heating sequence; Will The time lag corresponding to the preset threshold is taken as the effective time lag, that is, .

[0028] Furthermore, step S3 is specifically as follows: Fuzzification of input variables: Get temperature deviation value Determine the corresponding domain and use the triangular membership function to divide the corresponding fuzzy set into {negative large , negative small , zero , Zheng Xiao , Zhengda }; Get the rate of change of temperature deviation value Determine the corresponding domain, and use Gaussian membership function to divide the corresponding fuzzy set into {negative fast , negative slow ,zero , is slow , just fast }; A fuzzy inference library is constructed based on the fuzzy inference table corresponding to the temperature deviation value and its change rate; it is expressed as: Table 1 Examples of some rules Enter the real-time temperature deviation value and the rate of change of temperature deviation , based on the fuzzy reasoning library, obtain the corresponding fuzzy output of PID parameters; Defuzzification: The center of gravity method COG is used to convert the fuzzy output into accurate PID parameter adjustment, thereby completing the tuning of the PID parameters of the dynamic tuning PID controller.

[0029] Furthermore, the process flow of drilling and riveting includes drilling period, riveting period and tool withdrawal period in sequence. The change rate of temperature deviation value of the processing area during drilling period, riveting period and tool withdrawal period is Make sure the corresponding domains are different; Refer to Table 2, and build a process-oriented fuzzy rule base based on it; Table 2

[0030] Temperature deviation The corresponding domain is determined based on the melting point of the drilling and riveting material.

[0031] The present invention is described in detail above in conjunction with the embodiments of the accompanying drawings. A person skilled in the art can make various variations of the present invention according to the above description. Therefore, some details in the embodiments should not be construed as limiting the present invention, and the present invention shall be protected by the scope defined by the attached claims.

Claims

1. A dynamic thermal assistance method based on a fuzzy PID control algorithm of a time series, characterized in that: The following steps are involved: Step S1: collecting temperature data of the drilling and riveting processing area in real time; Step S2: comparing the temperature data with the current material combination temperature threshold value preset in the process parameter database, and calculating the temperature deviation value and its change rate; Step S3: Construct a fuzzy reasoning rule base, and dynamically adjust the PID parameters of the PID controller according to the temperature deviation value and its change rate based on the fuzzy rule base. The PID parameters include the proportional coefficient , integral coefficient and the differential coefficient ; Step S4: generating a control signal according to the adjusted PID parameters, adjusting the output power of the electromagnetic induction heating device, thereby dynamically controlling the temperature of the drilling and riveting processing area; In the heating process of step S4, a temperature-vibration coupling model based on an LSTM neural network is constructed, historical temperature data and historical vibration data are obtained, a heating sequence in the historical temperature data and a corresponding vibration sequence in the historical vibration data are obtained, and the cross-correlation is calculated to determine the effective time lag, and the heating sequence is used as input, and the vibration sequence after the effective time lag is used as a label, and the temperature-vibration coupling model is trained to obtain an optimized temperature-vibration coupling model; Importing the temperature rise sequence in step S4 into the temperature-vibration coupling model based on the LSTM neural network to obtain a predicted vibration rise sequence; dynamically adjusting the control force of the active damper according to the data of the vibration rise sequence; Step S5: Based on steps S1 to S4, the temperature and vibration of the drilling and riveting processing area are dynamically adjusted to obtain the riveting force curve in each drilling and riveting process, and the preset parameters of the fuzzy reasoning rule library are optimized by analyzing the stability of the riveting force curve.

2. The dynamic thermal assistance method based on the fuzzy PID control algorithm of time series according to claim 1 is characterized in that: The method for establishing the fuzzy reasoning rule base in step S3 is specifically as follows: The fuzzy set of temperature deviation value is defined as {negative large, negative small, zero, positive small, positive large}, and the fuzzy set of change rate is defined as {negative fast, negative slow, zero, positive slow, positive fast}; Construct a fuzzy rule table to map the temperature deviation value and its change rate to the adjustment weight of the PID parameters. The rule form is: If e is A and Δe is B, then Δ =C,Δ =D,Δ =E, where A and B are input fuzzy sets, and C, D, and E are output fuzzy sets; in, represents the temperature deviation value, Δe represents the rate of change of the temperature deviation value, Δ Indicates the change in the proportionality coefficient, Δ Indicates the change in the integral coefficient, Δ Indicates the change in the differential coefficient.

3. The dynamic thermal assistance method based on fuzzy PID control algorithm of time series according to claim 1 is characterized in that: The process parameter database includes: Preset temperature thresholds for different material combinations; The material combination includes at least two types: metal-metal and metal-composite materials; Thermophysical parameters of each material, including thermal conductivity, melting point and maximum allowable heat-affected zone width; Mapping relationship table between historical riveting quality data and temperature control parameters.

4. The dynamic thermal assistance method based on the fuzzy PID control algorithm of time series according to claim 1 is characterized in that: During the process of dynamically tuning the PID parameters in step S3: The adjustment weight of the proportional coefficient is positively correlated with the absolute value of the temperature deviation; The adjustment weight of the integral coefficient is negatively correlated with the absolute value of the rate of change of the temperature deviation value; The adjustment weight of the differential coefficient is positively correlated with the product of the temperature deviation value and the rate of change.

5. The dynamic thermal assistance method based on fuzzy PID control algorithm of time series according to claim 1 is characterized in that: The power regulation of the electromagnetic induction heating device adopts PWM pulse width modulation technology, and the corresponding relationship between power output and PID control signal satisfies: ； in, is the heating power at time t, Indicates the temperature deviation value at time t.

6. The dynamic thermal assistance method based on fuzzy PID control algorithm of time series according to claim 1 is characterized in that: The specific process of obtaining the temperature rise sequence in the historical temperature data and the corresponding vibration rise sequence in the historical vibration data, calculating the cross-correlation and thus determining the effective time lag is as follows: Get the mutual correlation coefficient between the temperature rise sequence and the vibration rise sequence, expressed as: in, Indicates that the heating sequence and the vibration sequence are delayed in time The mutual correlation coefficient under is the heating sequence in The temperature of the moment, The rising sequence is The amplitude of the moment, is the mean of the warming series, represents the mean of the rising vibration sequence, is the length of the time series, is the time lag, which indicates the number of delayed steps of the vibration-raising sequence relative to the heating sequence; Will The time lag corresponding to the preset threshold is taken as the effective time lag, that is, .

7. The dynamic thermal assistance method based on fuzzy PID control algorithm of time series according to claim 1 is characterized in that: Step S3 is specifically as follows: Fuzzification of input variables: Get temperature deviation value Determine the corresponding domain and use the triangular membership function to divide the corresponding fuzzy set into {negative large , negative small , zero , Zheng Xiao , Zhengda }; Get the rate of change of temperature deviation value Determine the corresponding domain, and use Gaussian membership function to divide the corresponding fuzzy set into {negative fast , negative slow ,zero , is slow , just fast }; Construct a fuzzy reasoning library based on the fuzzy reasoning table corresponding to the temperature deviation value and its change rate; Enter the real-time temperature deviation value and the rate of change of temperature deviation , based on the fuzzy reasoning library, obtain the corresponding fuzzy output of PID parameters; Defuzzification: The center of gravity method COG is used to convert the fuzzy output into accurate PID parameter adjustment, thereby completing the tuning of the PID parameters of the dynamic tuning PID controller.

8. The dynamic thermal assistance method based on the fuzzy PID control algorithm of time series according to claim 7 is characterized in that: The process of drilling and riveting includes drilling, riveting and tool withdrawal. The change rate of temperature deviation value in the processing area during drilling, riveting and tool withdrawal is Make sure the corresponding domains are different; Based on this, a process-oriented fuzzy rule base is constructed; Temperature deviation The corresponding domain is determined based on the melting point of the drilling and riveting material.

Images