Intelligent adjustment and control method and system for feeding parameters of photovoltaic cable extruder

Abstract

The present invention relates to the field of regulation and control, and in particular to an intelligent regulation and control method and system for feeding parameters of a photovoltaic cable extruder. The method comprises: collecting feeding parameters of a photovoltaic cable extruder during operation, constructing a first window with the feeding parameters at the current moment as the end of the window, and then adjusting the first window to obtain a second window; filtering the feeding parameters at the current moment according to the feeding parameters in the second window using a hample filtering algorithm; and adjusting the feeding parameters at the next moment using the filtered feeding parameters at the current moment as target parameters. The present invention effectively solves the problem of being unable to accurately and reasonably remove noise and thus making more reasonable adjustments to the feeding parameters.

Description

Technical Field

[0001] The present invention relates to the field of regulation and control, and more specifically, to a method and system for intelligently regulating and controlling feeding parameters of a photovoltaic cable extruder. Background Art

[0002] The extrusion process of the cable is the core link in the production of photovoltaic cables, which involves the precise control of multiple parameters, including feeding speed, temperature, pressure, etc. The adjustment of the extruder feeding system has an important impact on the quality of the cable's insulation layer, conductor, and outer sheath. In practical applications, the sensors and measuring equipment of the extruder feeding system will inevitably be interfered by various external and internal factors, such as electromagnetic interference, equipment vibration, temperature fluctuations, etc. These interferences may cause the signals measured by the sensors to be unstable and generate noise. Noise will not only interfere with the normal operation of the system, but may also lead to wrong judgments and inaccurate control. Therefore, before controlling the feeding parameters, it is first necessary to filter the parameters to remove these noises so that the control system can respond more accurately.

[0003] The patent document with the authorization announcement number of "CN117631530B" and the name of "Temperature Control Method for Cross-linked Cable Production" discloses the following method: first, the system performs self-check and obtains multiple parameter indicators and the range of parameter indicators for the temperature control of the target cross-linked cable production line extruder and catenary pipe, and uses the improved ant colony algorithm to optimize and obtain the optimal PID parameters, and then improves the PID controller, adds a filter to the calculation link of the improved PID controller, and obtains the parameters of the lead-lag filter, and then assigns the output of the PID controller and the system sampling to the gray prediction auxiliary controller for state prediction, and forms negative feedback to optimize the control performance of the system, so as to achieve fast response, high control accuracy, stable control effect, and strong anti-interference ability. Temperature control of the cross-linked cable production line extruder and catenary pipe.

[0004] The above method is only applicable to temperature control and does not take into account the different types of noise in the data. Therefore, it is impossible to accurately and reasonably eliminate the noise and make more reasonable adjustments to the feeding parameters. Summary of the invention

[0005] In order to solve the problem in the prior art that it is impossible to accurately and reasonably eliminate noise and thus more reasonably adjust the feeding parameters, the present invention provides solutions in the following aspects.

[0006] In a first aspect, the present invention provides a method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder, comprising: collecting feeding parameters of a photovoltaic cable extruder during operation, constructing a first window with the feeding parameters at the current moment as the end of the window, and then adjusting the first window to obtain a second window; filtering the feeding parameters at the current moment according to the feeding parameters in the second window using a hample filtering algorithm; adjusting the feeding parameters at the next moment using the filtered feeding parameters at the current moment as target parameters; wherein adjusting the first window to obtain the second window comprises: calculating a power spectrum of the feeding parameters of the first window; calculating the probability of occurrence of different values ​​in the power spectrum, and performing linear fitting on these probabilities using the least squares method; calculating the probability Y that the power spectrum conforms to a uniform distribution and the length of the second window. , , ,in, is the slope after straight line fitting, is the number of different values ​​in the power spectrum, is the probability of the value r appearing in the power spectrum, is the fitting value of the probability of the value r appearing after the straight line fitting, C is the number of feeding parameters in the first window, F is the average change rate of the feeding parameters in the first window, is the possibility threshold.

[0007] By collecting the feeding parameters of the photovoltaic cable extruder during operation and filtering the parameters using the Hampel filter method, noise and outliers can be effectively removed, thereby obtaining more accurate and stable feeding parameters at the current moment. By adjusting the first window and combining power spectrum analysis with least squares fitting, the statistical characteristics and distribution trends of the feeding parameters in the window can be accurately calculated. Real-time dynamic adjustment of the length of the second window can ensure that the parameters after Hampel filtering are more accurate, providing a reliable basis for adjusting the feeding parameters at the next moment.

[0008] Preferably, the average rate of change of the first window feeding parameter comprises: calculating the rate of change corresponding to each feeding parameter in the first window; calculating the average rate of change of the first window feeding parameter , , where F is the average rate of change of the feeding parameter in the first window, C is the number of feeding parameters in the first window, is the rate of change corresponding to the i-th feeding parameter in the first window.

[0009] Calculating the average rate of change of the feeding parameters in the first window is an important step, which not only helps to monitor the dynamic changes of the feeding process, but also provides an accurate basis for adjusting the system.

[0010] Preferably, the calculation of the change rate corresponding to each feeding parameter in the first window includes: ,in, represents the change rate corresponding to the i-th feeding parameter in the first window, , , represent the i-th, i-1-th, and i+1-th feeding parameters in the first window respectively, Indicates the distance between the first window The most recent extreme value of the feeding parameter.

[0011] By accurately calculating the change rate corresponding to the feeding parameters, the dynamic change trend of the feeding system can be accurately understood. When the feeding system has abnormal fluctuations or sudden changes, the change rate will increase significantly. By monitoring the change rate, abnormal situations can be detected in time.

[0012] Preferably, the calculation of the change rate corresponding to each feeding parameter in the first window includes: calculating the change rate corresponding to each feeding parameter in the first window , ,in, represents the change rate corresponding to the i-th feeding parameter in the first window, , They respectively represent the i-th and i-1-th feeding parameters in the first window.

[0013] Preferably, the feeding parameters of the photovoltaic cable extruder during operation include at least one of the following: feeding speed, feeding pressure, feeding flow rate or feeding temperature.

[0014] Preferably, adjusting the first window to obtain the second window includes: performing missing completion processing on the feeding parameters in the second window.

[0015] By completing the missing feeding parameters in the second window, the integrity of the data can be effectively ensured, thereby avoiding the impact of missing data on subsequent filtering and adjustment processes.

[0016] Preferably, the method of adjusting the feeding parameters at the next moment by using the filtered feeding parameters at the current moment as the target parameters includes: adjusting the feeding parameters at the next moment by using a PID algorithm.

[0017] By comprehensively utilizing the three control strategies of PID, the system can flexibly respond to various dynamic changes in the feeding process and realize an intelligent and efficient production process.

[0018] In a second aspect, the present invention also provides a photovoltaic cable extruder feeding parameter intelligent adjustment and control system, comprising: a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the above-mentioned photovoltaic cable extruder feeding parameter intelligent adjustment and control method.

[0019] The beneficial effect of the present invention is that by collecting the feeding parameters of the photovoltaic cable extruder during operation and filtering the parameters using the Hampel filtering method, noise and outliers can be effectively removed, thereby obtaining more accurate and stable feeding parameters at the current moment. By adjusting the first window and combining power spectrum analysis with least squares fitting, the statistical characteristics and distribution trends of the feeding parameters in the window can be accurately calculated. Real-time dynamic adjustment of the length of the second window can ensure that the parameters after Hampel filtering are more accurate, providing a reliable basis for adjusting the feeding parameters at the next moment. Using power spectrum analysis, least squares fitting and hample filtering technology, noise can be accurately and reasonably eliminated to make more reasonable adjustments to the feeding parameters at the next moment. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] By reading the following detailed description with reference to the accompanying drawings, the above and other objects, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-limiting manner, and the same or corresponding reference numerals represent the same or corresponding parts, wherein:

[0021] Figure 1 This is a flow chart of a method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder provided by an embodiment of the present invention;

[0022] Figure 2 It is a block diagram of an intelligent adjustment control system for feeding parameters of a photovoltaic cable extruder provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] The specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0025] Figure 1 The present invention provides a flow chart of a method for intelligently adjusting and controlling the feeding parameters of a photovoltaic cable extruder, which includes the following steps:

[0026] S101, collecting feeding parameters of the photovoltaic cable extruder during operation, constructing a first window with the current feeding parameters as the window end, and then adjusting the first window to obtain a second window.

[0027] The first window is adjusted to obtain the second window, including: calculating the power spectrum of the feeding parameters of the first window; calculating the probability of different values ​​appearing in the power spectrum, and performing linear fitting on these probabilities using the least squares method; calculating the probability Y that the power spectrum conforms to the uniform distribution and the length of the second window , , ,in, is the slope after straight line fitting, is the number of different values ​​in the power spectrum, is the probability of the value r appearing in the power spectrum, is the fitting value of the probability of the value r appearing after the straight line fitting, C is the number of feeding parameters in the first window, F is the average change rate of the feeding parameters in the first window, The end of the second window is still the current feeding parameter.

[0028] There are many feeding parameters when the photovoltaic cable extruder is running. Generally, the feeding speed, feeding pressure, feeding flow rate or feeding temperature are key factors to ensure the stability and efficiency of the extrusion process. The feeding speed is usually closely related to the production rate of the cable extrusion process, which directly affects the production capacity and quality of the extruded product. By controlling the feeding speed, the production efficiency can be improved, the product specifications can be controlled, and overload or blockage can be prevented. The feeding pressure refers to the pressure when the material passes through the feed port in the feeding system, which is usually related to the fluidity and density of the material. By controlling the feeding pressure, stable feeding can be ensured, the product density can be adjusted, and the quality of the photovoltaic cable can be ensured. The feeding flow rate refers to the amount of material entering the extruder per unit time, which is usually related to the feeding speed and feeding pressure. Controlling the feeding flow rate can ensure the stability of the extrusion process. By maintaining a consistent feeding flow rate, the production quality and specifications of each cable can be ensured to be consistent, and unqualified products can be avoided. Feeding temperature refers to the temperature of the raw material entering the extruder, which has an important influence on the fluidity, viscosity and quality of the final product. Controlling the feeding temperature can keep the raw material in proper fluidity, ensure that the material can pass through the extruder smoothly, and form the expected shape with the mold, prevent blockage and material accumulation, and improve product quality. Therefore, in some embodiments, the feeding parameters of the photovoltaic cable extruder during operation include at least one of the following: feeding speed, feeding pressure, feeding flow rate or feeding temperature.

[0029] For example, by installing sensors on a photovoltaic cable extruder, the collected feeding parameters are: , , , , , , , , the current feeding parameters are , the preset first window length is 5, then As the end of the first window, the first window includes , , , , There are 5 feeding parameters in total.

[0030] When adjusting the first window to obtain the second window, it is necessary to first calculate the power spectrum of the feeding parameters of the first window, specifically: perform Fourier transform on each feeding parameter in the first window to obtain the corresponding frequency domain, and the square of the modulus of the frequency domain is the power spectrum corresponding to the feeding parameter. Fourier transform is a well-known method and will not be described here. After obtaining the power spectrum corresponding to each feeding parameter, calculate the probability of occurrence of each value in the power spectrum, and use the least squares method to perform linear fitting on these probabilities. For example, there are five feeding parameters in the first window, which are , , , , , the corresponding power spectrum is , , , , ,in and If the values ​​are equal, then there are 2 values, the probability of this value is 0.4, and the probability of the other three power spectra is 0.2. When the least squares method is used to fit the above power spectrum values ​​and the corresponding probabilities, the independent variable is the power spectrum value and the dependent variable is the corresponding probability. The specific fitting process belongs to the well-known method and will not be described here. After the straight line fitting, the slope of the fitting line can be obtained. For each power spectrum value, there will also be a corresponding fitting probability. Combined with the above formula The possibility that the power spectrum of the extruder feeding parameters conforms to the uniform distribution can be calculated. The greater the possibility that the power spectrum of the feeding parameters conforms to the uniform distribution, the closer the noise in the feeding parameters is to white noise, and the smaller the window length required for filtering. Otherwise, the closer the noise in the feeding parameters is to colored noise, the larger the window length required for filtering. Therefore, the calculation formula for the second window length can be set , is the possibility threshold, which is used as the boundary to judge whether the noise in the feeding parameters is closer to white noise or colored noise.

[0031] The average rate of change of the first window feed parameter is required when calculating the second window length. In some embodiments, the method for calculating the average rate of change includes: calculating the rate of change corresponding to each feed parameter in the first window; calculating the average rate of change of the first window feed parameter , , where F is the average rate of change of the feeding parameter in the first window, C is the number of feeding parameters in the first window, is the change rate corresponding to the i-th feeding parameter in the first window. The present invention provides two methods for calculating the change rate corresponding to each feeding parameter in the first window. The first method is: ,in, represents the change rate corresponding to the i-th feeding parameter in the first window, , , represent the i-th, i-1-th, and i+1-th feeding parameters in the first window respectively, Indicates the distance between the first window The most recent extreme value of the feeding parameter. It reflects the difference between the i-th feeding parameters of the photovoltaic cable extruder and the feeding parameters of the photovoltaic cable extruder collected at adjacent times. It reflects the difference between the extreme value of the i-th feeding parameter of the photovoltaic cable extruder and the feeding parameter of the nearest neighbor. The larger the ratio of the two, the closer the i-th feeding parameter is to the extreme value of its nearest neighbor, and the larger the difference with the feeding parameter at adjacent moments, indicating that the system has undergone a large change in a short period of time. Consider the current rate of change and the relative position to the nearest extreme value at the same time. By calculating the change amount at adjacent moments and comparing it with the difference of the extreme values, the change trend and amplitude of the feeding parameters can be more accurately characterized. The second method is a simple method to calculate the rate of change corresponding to the feeding parameters, specifically: ,in, represents the change rate corresponding to the i-th feeding parameter in the first window, , They respectively represent the i-th and i-1-th feeding parameters in the first window.

[0032] After obtaining the second window, in order to prevent certain parameters in the second window from affecting the subsequent filtering and adjustment process, it is necessary to complete the missing feeding parameters in the second window to ensure the integrity of the data. Generally, the interpolation completion method can be used.

[0033] S102: Filter the current feeding parameters according to the feeding parameters in the second window using a Hample filtering algorithm.

[0034] The conventional Hample filtering method is usually based on a fixed window length. In the present invention, the length of the second window is adjusted dynamically in real time, so that the parameters after the Hample filtering can be made more accurate.

[0035] The feeding parameters at the current moment are filtered according to the feeding parameters in the second window using the Hample filtering algorithm, specifically: the median deviation of the feeding parameters in the second window is calculated, and when the median deviation is less than or equal to a threshold value, the feeding parameters at the current moment are used as the filtered feeding parameters at the current moment; when the median deviation is greater than the threshold value, the median of the feeding parameters in the second window is used as the filtered feeding parameters at the current moment.

[0036] S103, using the filtered feeding parameters at the current moment as target parameters to adjust the feeding parameters at the next moment.

[0037] In this step, the PID algorithm can generally be used to adjust the feeding parameters at the next moment. It should be noted that the PID algorithm belongs to the known technology and will not be described in detail here.

[0038] The above-mentioned intelligent adjustment and control method for feeding parameters of a photovoltaic cable extruder provided by an embodiment of the present invention can effectively remove noise and outliers by collecting the feeding parameters of the photovoltaic cable extruder during operation and filtering the parameters using the Hampel filtering method, thereby obtaining more accurate and stable feeding parameters at the current moment. By adjusting the first window and combining power spectrum analysis with least squares fitting, the statistical characteristics and distribution trends of the feeding parameters in the window can be accurately calculated. Real-time dynamic adjustment of the length of the second window can ensure that the parameters after Hampel filtering are more accurate, providing a reliable basis for adjusting the feeding parameters at the next moment. Using power spectrum analysis, least squares fitting and hample filtering technology, noise can be accurately and reasonably eliminated to make more reasonable adjustments to the feeding parameters at the next moment.

[0039] The present invention also provides a photovoltaic cable extruder feeding parameter intelligent adjustment control system. Figure 2 As shown, the system includes a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder described in the present invention is implemented.

[0040] The system also includes other components familiar to those skilled in the art, such as a communication bus and a communication interface, whose configuration and functions are known in the art and thus will not be described in detail here.

[0041] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, apparatus or device. For example, a computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory RRAM (Resistive Random Access Memory), a dynamic random access memory DRAM (Dynamic Random Access Memory), a static random access memory SRAM (Static Random-Access Memory), an enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), a high-bandwidth memory HBM (High-Bandwidth Memory), a hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of a device or accessible or connectable to a device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.

[0042] In the description of this specification, "plurality" or "several" means at least two, such as two, three or more, etc., unless otherwise clearly and specifically defined.

[0043] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

Claims

1. A method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder, characterized in that: include: Collecting the feeding parameters of the photovoltaic cable extruder during operation, constructing a first window with the current feeding parameters as the window end, and then adjusting the first window to obtain a second window; Using the Hample filtering algorithm to filter the current feeding parameters according to the feeding parameters in the second window; Using the filtered feeding parameter at the current moment as the target parameter to adjust the feeding parameter at the next moment, including: using a PID algorithm to adjust the feeding parameter at the next moment; The first window is adjusted to obtain the second window, including: calculating the power spectrum of the feeding parameters of the first window; calculating the probability of different values ​​appearing in the power spectrum, and performing linear fitting on these probabilities using the least squares method; calculating the probability Y that the power spectrum conforms to the uniform distribution and the length of the second window , , ,in, is the slope after straight line fitting, is the number of different values ​​in the power spectrum, is the probability of the value r appearing in the power spectrum, is the fitting value of the probability of the value r appearing after the straight line fitting, C is the number of feeding parameters in the first window, F is the average change rate of the feeding parameters in the first window, is the possibility threshold; The average rate of change of the first window feeding parameters includes: Calculate the change rate corresponding to each feeding parameter in the first window; calculate the average change rate of the feeding parameters in the first window , , where C is the number of feeding parameters in the first window, is the rate of change corresponding to the i-th feeding parameter in the first window.

2. The method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder according to claim 1 is characterized in that: The calculating the change rate corresponding to each feeding parameter in the first window includes: ,in, represents the change rate corresponding to the i-th feeding parameter in the first window, , , represent the i-th, i-1-th, and i+1-th feeding parameters in the first window respectively, Indicates the distance between the first window The most recent extreme value of the feeding parameter.

3. The method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder according to claim 1 is characterized in that: The calculating the change rate corresponding to each feeding parameter in the first window includes: Calculate the change rate of each feeding parameter in the first window , ,in, represents the change rate corresponding to the i-th feeding parameter in the first window, , They respectively represent the i-th and i-1-th feeding parameters in the first window.

4. The method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder according to claim 1 is characterized in that: The feeding parameters of the photovoltaic cable extruder during operation include at least one of the following: Feeding speed, feeding pressure, feeding flow or feeding temperature.

5. The method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder according to claim 1 is characterized in that: The first window is adjusted to obtain the second window, including: performing missing completion processing on the feeding parameters in the second window.

6. An intelligent control system for feeding parameters of a photovoltaic cable extruder, characterized in that: include: A memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement the method for intelligently adjusting and controlling feeding parameters of a photovoltaic cable extruder as described in any one of claims 1 to 5.

Images