Control method and system for felt fabric production line

Abstract

The invention discloses a control method and system for a felt fabric production line, and relates to the technical field of intelligent control, and the method comprises the following steps: analyzing the requirements of the felt fabric production line, including the requirements of a needling reinforcement process and the target strength and uniformity of felt fabrics; according to the control method and system for the felt fabric production line, various data in the production process, including equipment parameters of a needling machine and environmental parameter data of the felt fabric production line, are collected through a sensor, and the data are input into an interference prediction model after being cleaned and preprocessed, so that monitoring and prediction of the production process are realized; the accuracy and timeliness of production control are greatly improved, measures can be taken immediately at the beginning of abnormal fluctuation, production accidents and decline of product quality are effectively avoided, and meanwhile, the intelligent control strategy automatically adjusts parameters of the needling machine according to real-time data, optimizes the production process and improves the consistency of production efficiency and product quality.

Description

Technical Field

[0001] The present invention relates to the field of intelligent control technology, and in particular to a control method and system for a felt fabric production line. Background Art

[0002] With the advancement of science and technology and the rapid development of industry, felt fabrics, as a new type of material, have been widely used in many fields with their unique performance advantages. The production technology of felt fabrics has been continuously updated, production efficiency and quality have been continuously improved, and market demand has continued to grow. This trend has promoted the automation and intelligent development of felt fabric production lines and put forward higher requirements on control methods. The production process of felt fabrics involves multiple links and multiple equipment, such as raw material preparation, fiber transportation, web formation, reinforcement, post-processing, etc. The interaction and coordination relationship between each link and equipment is complex, which further increases the complexity of felt fabric production control.

[0003] In the prior art, during the needle punching reinforcement process of felt fabrics, the speed, depth and frequency parameters of the needle punching machine need to be precisely controlled to ensure the strength and uniformity of the felt fabrics. However, due to various uncertainties in the production process, the control difficulty increases. Therefore, how to reduce the uncertainties and interference factors in the production process of felt fabrics is a problem we need to solve. To this end, a control method and system for a felt fabric production line are proposed. Summary of the invention

[0004] To achieve the above objectives, the present invention is implemented through the following technical solutions: In the first aspect, a control method for a felt fabric production line comprises the following steps:

[0005] Step 1: Analyze the requirements of the felt fabric production line, including the requirements of the needle punching reinforcement process, the target strength and uniformity of the felt fabric, and set the initial speed, depth and frequency parameters of the needle punching machine to determine the reasonable fluctuation range of the parameters;

[0006] Step 2: Collect the original data of the equipment parameters and environmental parameters of the acupuncture machine, and pre-process the collected original data to ensure the accuracy and reliability of the data, wherein the original data is divided into historical data and real-time data, the equipment parameters include the speed, depth, and frequency of the acupuncture machine, and the environmental parameters include ambient temperature and humidity;

[0007] Step 3: Based on historical data and real-time data, an interference prediction model between needle loom parameters and felt fabric quality is established, and the interference prediction model is used to predict the future state of the needle loom, including the changing trends of speed, depth and frequency, as well as anomalies and fluctuations in the production process;

[0008] Step 4: Combine historical data to preset the abnormal fluctuation levels of the needle loom, which are low abnormal fluctuation level, medium abnormal fluctuation level and high abnormal fluctuation level, and match the corresponding fluctuation threshold for each abnormal fluctuation level, and formulate a corresponding intelligent control strategy, which can automatically adjust the speed, depth and frequency of the needle loom to cope with uncertainties and interference factors in the production process, and ensure that the strength and uniformity of the felt fabric meet the requirements;

[0009] Step 5. Input real-time data into the interference prediction model, analyze the current state of the needle loom and the level of abnormal fluctuation, implement the corresponding intelligent control strategy to control the needle loom, continuously monitor the quality indicators of felt fabrics, such as strength and uniformity, and compare the monitoring results with the expected goals. According to the comparison results, adjust the control strategy in time to eliminate deviations and ensure the stability of the production process and the consistency of product quality.

[0010] In a second aspect, a control system for a felt fabric production line is provided, which is used to implement a control method for a felt fabric production line, and includes a control center, wherein the control center is communicatively connected to a data acquisition and processing module, an interference prediction module, an abnormality determination module, an intelligent control module, a quality monitoring module, and an early warning notification module, wherein electrical signals are connected between the modules;

[0011] The data acquisition and processing module is used to collect the equipment parameters of the needle-loom machine and the environmental parameters of the felt fabric production line through sensors, and pre-process the collected data to provide an accurate and reliable basis for subsequent interference prediction and control strategy adjustment;

[0012] The interference prediction module uses historical data and real-time data to predict the future state and parameter change trend of the needle loom, identify potential production fluctuations and anomalies in advance, and provide a scientific basis for the control strategy;

[0013] The abnormality determination module calculates the abnormal fluctuation coefficient according to the output of the interference prediction model, and determines the current abnormal fluctuation level, providing clear level guidance for implementing corresponding control strategies;

[0014] The intelligent control module automatically executes the preset control strategy according to the abnormal fluctuation level, such as adjusting the needling machine parameters or sending early warning notifications, to ensure the stability of the production process and the consistency of product quality, and reduce manual intervention;

[0015] The quality monitoring module is used to continuously monitor the quality indicators of felt fabrics, such as strength, uniformity, thickness, etc., to ensure that product quality meets standard requirements, and to record and feed back the monitoring results to the control center in real time to provide data support for the adjustment of control strategies;

[0016] The warning notification module sends a warning notification to the operator in a timely manner when an abnormality occurs or is about to occur in the production process. The notification content includes the type of abnormality, the scope of impact and the recommended response measures, helping the operator to quickly respond and handle the problem.

[0017] The present invention provides a control method and system for a felt fabric production line, which has the following beneficial effects:

[0018] 1. The control method and system of the felt fabric production line collect various data in the production process through sensors, including the equipment parameters of the needle loom and the environmental parameter data of the felt fabric production line. After cleaning and preprocessing, the data is input into the interference prediction model to realize the monitoring and prediction of the production process, greatly improving the accuracy and timeliness of production control, and being able to take measures immediately when abnormal fluctuations begin to appear, effectively avoiding the occurrence of production accidents and the decline of product quality. At the same time, the intelligent control strategy automatically adjusts the parameters of the needle loom according to real-time data, optimizes the production process, and improves production efficiency and product quality consistency.

[0019] 2. The control method and system of the felt fabric production line can realize accurate detection and graded response to abnormal fluctuations of the felt fabric production line through multi-dimensional data analysis and machine learning algorithms, comprehensively consider the interaction and influence of multiple parameters, and more comprehensively evaluate the stability of the production process. When abnormal fluctuations are detected, the abnormal fluctuation level is judged according to the preset grading standards, and the corresponding control strategy is triggered. The graded response mechanism not only avoids the waste of resources caused by excessive intervention, but also ensures that effective measures can be taken quickly in the event of high abnormal fluctuations to ensure production safety and quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Figure 1 A method flow chart of a control method and system for a felt fabric production line of the present invention;

[0021] Figure 2 A flow chart for establishing an interference prediction model of the present invention;

[0022] Figure 3 A flow chart for formulating the intelligent control strategy of the present invention;

[0023] Figure 4 It is a module diagram of the present invention. DETAILED DESCRIPTION

[0024] The present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments. The embodiments of the present invention are provided for the purpose of illustration and description, and are not intended to be exhaustive or to limit the present invention to the disclosed forms. Many modifications and variations will be apparent to those of ordinary skill in the art. The embodiments are selected and described in order to better illustrate the principles and practical applications of the present invention, and to enable those of ordinary skill in the art to understand the present invention and thereby design various embodiments with various modifications suitable for specific uses.

[0025] The first embodiment, as Figure 1 , Figure 2 As shown, the present invention provides a technical solution: a control method for a felt fabric production line, comprising the following steps:

[0026] Step 1. Analyze the needs of the felt fabric production line, including the requirements of the needle punching reinforcement process, the target strength and uniformity of the felt fabric, and set the initial speed, depth and frequency parameters of the needle punching machine, determine the reasonable fluctuation range of the parameters, determine the physical and chemical performance requirements of the felt fabric according to its purpose, and analyze the target strength and uniformity of the felt fabric. On the basis of the analysis of the target strength and uniformity of the felt fabric, analyze the impact of the needle punching reinforcement process on the performance of the felt fabric to determine the key parameters of the needle punching reinforcement process, which are the needle punching speed, needle punching depth and needle punching frequency of the needle punching machine. According to the requirements of the needle punching reinforcement process and the performance targets of the felt fabric, set the initial speed, depth and frequency parameters of the needle punching machine. The initial speed is set according to the type and thickness of the raw fiber, the target output and the matching of other equipment of the production line. It is initially set to a moderate speed value, and the depth is based on the thickness of the fiber layer and the required reinforcement degree. The initial value is set to 70%-80% of the fiber layer thickness to ensure that the needle punching can penetrate the fiber layer and form effective interweaving. The initial value of the frequency is set according to the speed to ensure that the needle punching action is continuous and stable. The factors affecting the parameters of the needle punching machine in the production process are analyzed to determine the reasonable fluctuation range of the speed, depth and frequency parameters to ensure that the performance of the felt fabric can still meet the requirements within the fluctuation range. The speed fluctuation range is within ±10% to cope with minor fluctuations caused by factors such as raw material changes and equipment wear. The depth fluctuation range is within ±5% to ensure the consistency of the needle punching depth and avoid quality problems caused by too deep or too shallow. The frequency fluctuation range is automatically adjusted according to the speed fluctuation to maintain coordination and stability with the speed. A small batch trial production is carried out under the set initial parameters to verify the rationality of the parameter setting, and the trial production data is analyzed to determine the performance of the felt fabric under the current parameter settings.

[0027] Step 2: Collect the original data of the equipment parameters and environmental parameters of the acupuncture machine, and pre-process the collected original data to ensure the accuracy and reliability of the data. The original data is divided into historical data and real-time data. The equipment parameters include the speed, depth, and frequency of the acupuncture machine. The environmental parameters include ambient temperature and humidity. The data type to be collected is clarified, including the speed, depth, and frequency equipment parameters of the acupuncture machine, as well as the ambient temperature and humidity environmental parameters. According to the data type, corresponding sensors are deployed in the acupuncture machine and the production environment in which it is located to obtain the corresponding data. The original data of the equipment parameters and environmental parameters of the acupuncture machine are obtained through the deployed sensors. The original data is divided into historical data and real-time data. The historical data retrieves the historical equipment parameters and environmental parameters data from the database, log files, and archived records. The real-time data continuously collects the equipment and environmental parameter data at the current moment through sensors. The acupuncture speed data is obtained through the sensors of the acupuncture machine. The depth sensor installed on the acupuncture machine is used to monitor the acupuncture speed. The actual insertion depth of the needle, the frequency data of the needling action is read from the control system of the needling machine, the equipment parameter data of the needling machine is comprehensively obtained, the ambient temperature is monitored on the production line using a temperature sensor, and the ambient humidity data of the production line area is collected using a humidity sensor to obtain the environmental parameter data, and the collected equipment parameter and environmental parameter data of the needling machine are preprocessed, including data cleaning, data calibration and data normalization. Data cleaning identifies and deletes data points that are beyond a reasonable range or are obviously wrong, such as speed is negative, depth is much greater than the fiber layer thickness, etc. For missing data points, interpolation is used to fill them in, and the sensors of the needling machine are calibrated regularly to ensure the accuracy and stability of their measurements, and the accuracy of the temperature and humidity sensors is confirmed. The equipment parameters and environmental parameters of different dimensions and ranges are converted to a unified scale for subsequent data analysis and processing, and the preprocessed equipment parameter and environmental parameter data of the needling machine are stored in the data warehouse for subsequent query, analysis and modeling;

[0028] Step 3. Based on historical data and real-time data, establish an interference prediction model between the needle loom parameters and the quality of felt fabrics, and use the interference prediction model to predict the future state of the needle loom, including the changing trends of speed, depth and frequency, as well as anomalies and fluctuations in the production process. Traverse the pre-processed needle loom equipment parameter and environmental parameter data, extract the historical equipment parameter data, environmental parameter data of the needle loom and the quality inspection data of felt fabrics in the corresponding time period from the historical data, and mark the abnormal point data in the extracted historical data. Combined with the historical data and the marked abnormal point data, analyze the relationship between the needle loom equipment parameters and the quality of felt fabrics and the interference of environmental parameters on the quality of felt fabrics, and extract the equipment features and environmental features that affect the quality of felt fabrics to form an equipment feature set and an environmental feature set. Based on the relevant data of the equipment feature set and the neural network model, build an equipment control Model, predict the future state and parameter change trend of the needle loom, build an environmental interference model based on the relevant data of the environmental feature set combined with the decision tree model, analyze the interference of environmental factors on the production quality of felt fabrics, combine the equipment control model and the relevant data of the equipment feature set, analyze and obtain the equipment control index, predict the change trend of the speed, depth and frequency of the needle loom, combine the environmental interference model and the relevant data of the environmental feature set to obtain the environmental interference index, analyze the degree of influence of environmental factors on the production quality of felt fabrics, extract the associated data of the equipment control index and the environmental interference index, use historical data as the training set, conduct model training, build an interference prediction model, and combine the values ​​of the equipment control index and the environmental interference index with the interference prediction model to obtain the abnormal fluctuation coefficient, predict the abnormalities and fluctuations in the production process of felt fabrics, and analyze the abnormal production quality risks under the joint action of equipment and environment;

[0029] Furthermore, the expression of the device control index is:

[0030]

[0031] Among them, ECI is the equipment control index, which is used to evaluate the control of acupuncture machine parameters, n is the number of equipment parameters, and w i is the weight of the i-th parameter, reflecting the influence of this parameter on the quality of felt fabrics. The sum of the weights is 1. Ac i is the actual measured value of the i-th parameter, indicating the currently measured device parameter value. i is the reference value of the i-th parameter, that is, the value under the optimal operating conditions, Trs iis the maximum allowable value of the reasonable fluctuation range of the ith parameter, indicating the allowable fluctuation range of the equipment parameter. α is the adjustment coefficient, which is used to adjust the influence of the factor on ECI. The value range of ECI is 0 to 1, where 0 means that all equipment parameters are in an ideal state, and 1 means that at least one parameter exceeds the reasonable fluctuation range. The smaller the ECI value, the better the equipment control and the more stable the production process. For each equipment parameter, calculate the deviation between its actual value and the benchmark value, compare each deviation with the reasonable fluctuation range of the parameter, and take the smaller value to ensure that even if the deviation is large, the calculation result will not exceed the maximum allowable value of the set reasonable fluctuation range. According to the importance of each parameter, the weight w is used to calculate the value of the reference value. i Adjust the deviation, adjust the influence of the deviation through the index α, make ECI more sensitive to small changes in parameters, sum up all the adjusted deviation values ​​to get the final equipment control index, and comprehensively evaluate the equipment parameter control of the needle loom through the equipment control index to provide guidance for the optimization of the production process;

[0032] The expression of environmental interference index is:

[0033]

[0034] Among them, EII is the environmental interference index, which is used to evaluate the impact of environmental factors on the production quality of felt fabrics, m is the number of environmental parameters, v is the number of environmental parameters, and v is the number of environmental parameters. j is the weight of the jth environmental parameter, reflecting the influence of this parameter on the quality of felt fabrics. The sum of the weights is 1, indicating the importance of different environmental parameters. j is the actual measured value of the jth environmental parameter, indicating the currently measured environmental parameter value, Tar j is the target value of the jth environmental parameter, that is, the value under the optimal operating conditions, indicating the environmental parameter value under ideal conditions, Tol j is the maximum allowable value of the reasonable fluctuation range of the jth environmental parameter, indicating the allowable fluctuation range of the environmental parameter. k is a constant used to adjust the sensitivity of the exponential function. The value range of EII is 0 to 1, where 0 means that all environmental parameters are in an ideal state, and 1 means that at least one environmental parameter exceeds the reasonable fluctuation range. The smaller the EII value, the better the environmental control and the more stable the production process. For each environmental parameter, calculate the deviation between its actual value and the target value, compare each deviation with the reasonable fluctuation range of the parameter, and take the smaller value to ensure that even if the deviation is large, the calculation result will not exceed the maximum allowable value of the set reasonable fluctuation range. According to the importance of each parameter, the weight v is used to calculate the value of the target value. j To adjust the deviation, use the exponential function e -k·V The degree of influence of adjustment deviation, Where V is the standardized deviation, which makes EII insensitive to small deviations, but increases rapidly for large deviations, reflecting the impact of environmental parameters deviating from the ideal state. All adjusted deviation values ​​are summed to obtain the final environmental interference index EII. Through the environmental interference index, the impact of environmental factors on the production process of felt fabrics is comprehensively evaluated, providing guidance for the optimization of the production environment.

[0035] Furthermore, the expression of the abnormal volatility coefficient is:

[0036]

[0037] Among them, AFC is the abnormal fluctuation coefficient, n is the number of equipment parameters, m is the number of environmental parameters, and w i is the weight of the i-th device parameter, v j is the weight of the jth environmental parameter, ECI i is the equipment control index of the ith equipment parameter, EII j is the environmental interference index of the jth environmental parameter, x is a variable tending to infinity, which is used to adjust the limit behavior of the exponential function. The larger the AFC value, the higher the possibility of abnormalities and fluctuations in the production process. According to the importance of each equipment parameter and environmental parameter, the weight w is used to adjust the limit behavior of the exponential function. i and v j Adjust ECI and EII using exponential functions and The effect of each exponent is amplified as x tends to infinity, making AFC very sensitive to small changes in ECI and EII, through the limiting function Calculate AFC to ensure that AFC can reflect long-term trends and potential abnormal fluctuations. Sum all adjusted index values ​​to obtain the final abnormal fluctuation coefficient AFC.

[0038] Step 4: Combine historical data to preset the abnormal fluctuation levels of the needle loom, which are low abnormal fluctuation level, medium abnormal fluctuation level and high abnormal fluctuation level, and match the corresponding fluctuation threshold for each abnormal fluctuation level, and formulate a corresponding intelligent control strategy, which can automatically adjust the speed, depth and frequency of the needle loom to cope with uncertainties and interference factors in the production process, and ensure that the strength and uniformity of the felt fabric meet the requirements;

[0039] Step 5. Input real-time data into the interference prediction model, analyze the current state of the needle loom and the level of abnormal fluctuation, implement the corresponding intelligent control strategy to control the needle loom, continuously monitor the quality indicators of felt fabrics, such as strength and uniformity, and compare the monitoring results with the expected goals. According to the comparison results, adjust the control strategy in time to eliminate deviations and ensure the stability of the production process and the consistency of product quality.

[0040] The second embodiment is based on the first embodiment. Figure 3 As shown, in step 4, the process of formulating the intelligent control strategy includes:

[0041] According to the distribution of historical data and abnormal fluctuation coefficients, three abnormal fluctuation levels are set: low abnormal fluctuation level, medium abnormal fluctuation level and high abnormal fluctuation level, and each abnormal fluctuation level corresponds to a fluctuation threshold range. The low abnormal fluctuation level means that when the abnormal fluctuation coefficient is lower than a lower threshold, the production process is considered to be relatively stable with small fluctuations. The medium abnormal fluctuation level means that when the abnormal fluctuation coefficient is between the lower threshold and the higher threshold, it means that there is a certain degree of fluctuation in the production process, but it is still within the controllable range. The high abnormal fluctuation level means that when the abnormal fluctuation coefficient is higher than the higher threshold, it means that there is a significant fluctuation in the production process, and immediate measures need to be taken to adjust it. According to different abnormal fluctuation levels, corresponding intelligent control strategies are formulated to automatically adjust the speed, depth and frequency of the acupuncture machine. Low abnormal fluctuation level: keep the current speed, depth and frequency of the acupuncture machine unchanged, or proceed Fine-tune to maintain the best production status, monitor production data, and be prepared to respond quickly when fluctuations increase. Medium abnormal fluctuation level: automatically adjust the parameters of the needle loom according to the cause of the fluctuation (such as changes in equipment parameters, ambient temperature fluctuations, etc.), send early warning notifications to operators to understand the production status and prepare for further intervention. High abnormal fluctuation level: immediately take emergency measures, such as suspending production, adjusting the needle loom to safe mode or switching to a backup production line, automatically analyze the cause of the fluctuation, and try to restore production stability by adjusting parameters. If the automatic adjustment is ineffective, notify the operator to intervene manually, record abnormal events and measures taken for subsequent analysis and improvement, and integrate intelligent control strategies into the control system of the felt fabric production line to achieve automated monitoring and adjustment, monitor production data and abnormal fluctuation coefficients, and ensure accurate judgment of the current abnormal fluctuation level and take corresponding control measures.

[0042] Further, the multiple abnormal fluctuation levels correspond to multiple fluctuation thresholds, wherein the fluctuation threshold includes an upper threshold and a lower threshold;

[0043] Multiple abnormal fluctuation levels and multiple fluctuation thresholds satisfy the following relationship:

[0044] Low abnormal fluctuation level AFC≤AFC M ;

[0045] Medium Abnormal Fluctuation Level AFC M <AFC≤AFC H ;

[0046] High abnormal fluctuation level AFC>AFC H ;

[0047] Among them, AFC is the abnormal volatility coefficient, AFC M is the upper threshold corresponding to the low abnormal fluctuation level and the lower threshold corresponding to the medium abnormal fluctuation level, AFC H The upper threshold corresponding to the medium abnormal fluctuation level and the lower threshold corresponding to the high abnormal fluctuation level;

[0048] In step 5, the process of implementing the intelligent control strategy to control the needle loom includes:

[0049] Through the sensors installed in the needle loom and felt fabric production line environment, the equipment parameters and environmental parameter data of the needle loom are collected in real time, the collected real-time data are cleaned and preprocessed, and the preprocessed real-time data are input into the interference prediction model to analyze the current state of the needle loom, including predicting the changing trend of the equipment parameters and environmental parameters. According to the output of the interference prediction model, the abnormal fluctuation coefficient is calculated, and the abnormal fluctuation level of the current production process is judged in combination with the preset fluctuation threshold. According to the judged abnormal fluctuation level, the corresponding intelligent control strategy is automatically executed, and the quality indicators of felt fabrics are continuously monitored. The monitoring results are recorded in the data warehouse in real time for subsequent analysis and comparison. The expected quality targets of felt fabrics are set according to production requirements and product standards, and the quality indicators actually monitored are compared with the expected targets. The stability of the production process and the consistency of product quality are evaluated. If there are deviations, the causes are analyzed and the control strategy is adjusted according to the analysis results.

[0050] The third embodiment is based on the first and second embodiments. Figure 4 As shown, the present invention also provides a technical solution: a control system for a felt fabric production line, used to implement a control method for a felt fabric production line, including a control center, the control center is communicatively connected with a data acquisition and processing module, an interference prediction module, an abnormality determination module, an intelligent control module, a quality monitoring module and an early warning notification module, wherein the modules are electrically connected by signals;

[0051] The data acquisition and processing module is used to collect the equipment parameters of the needle-loom machine and the environmental parameters of the felt fabric production line through sensors, and pre-process the collected data to provide an accurate and reliable basis for subsequent interference prediction and control strategy adjustment;

[0052] The interference prediction module uses historical data and real-time data to predict the future state and parameter change trend of the needle loom, identify potential production fluctuations and anomalies in advance, and provide a scientific basis for the control strategy;

[0053] The abnormality determination module calculates the abnormal fluctuation coefficient according to the output of the interference prediction model, and determines the current abnormal fluctuation level, providing clear level guidance for the implementation of corresponding control strategies;

[0054] Intelligent control module, according to the abnormal fluctuation level, automatically executes the preset control strategy, such as adjusting the needling machine parameters or sending early warning notifications, to ensure the stability of the production process and the consistency of product quality, and reduce manual intervention;

[0055] The quality monitoring module is used to continuously monitor the quality indicators of felt fabrics, such as strength, uniformity, thickness, etc., to ensure that the product quality meets the standard requirements, and to record and feed back the monitoring results to the control center in real time to provide data support for the adjustment of control strategies;

[0056] The early warning notification module sends early warning notifications to operators in a timely manner when an abnormality occurs or is about to occur during the production process. The notification content includes the type of abnormality, the scope of impact, and recommended response measures to help operators respond quickly and handle problems.

[0057] Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field and related fields without creative work should fall within the scope of protection of the present invention. The structures, devices and operating methods not specifically described and explained in the present invention are implemented according to the conventional means in the field unless otherwise specified and limited.

Claims

1. A control method for a felt fabric production line, characterized in that: The following steps are involved: Step 1: Analyze the requirements of the felt fabric production line, including the requirements of the needle punching reinforcement process, the target strength and uniformity of the felt fabric, and set the initial speed, depth and frequency parameters of the needle punching machine to determine the reasonable fluctuation range of the parameters; Step 2: Collecting the original data of the equipment parameters and environmental parameters of the acupuncture machine, and preprocessing the collected original data, wherein the original data is divided into historical data and real-time data, the equipment parameters include the speed, depth and frequency of the acupuncture machine, and the environmental parameters include the ambient temperature and humidity; Step 3: Based on historical data and real-time data, an interference prediction model between needle loom parameters and felt fabric quality is established, and the interference prediction model is used to predict the future state of the needle loom, including the changing trends of speed, depth and frequency, as well as anomalies and fluctuations in the production process; Step 4: Combine historical data to preset abnormal fluctuation levels of the acupuncture machine, which are low abnormal fluctuation level, medium abnormal fluctuation level and high abnormal fluctuation level, and match corresponding fluctuation thresholds for each abnormal fluctuation level, and formulate corresponding intelligent control strategies; Step 5: Input the real-time data into the interference prediction model, analyze the current state and abnormal fluctuation level of the acupuncture machine, and implement the intelligent control strategy to control the acupuncture machine.

2. The control method of a felt fabric production line according to claim 1, characterized in that: In step 1, the process of setting the initial speed, depth and frequency parameters of the acupuncture machine includes: Determine the physical and chemical property requirements of felt fabrics and analyze the target strength and uniformity; Analyze the effect of needle punching process on the properties of felt fabrics to determine the speed, depth and frequency of needle punching; According to the process requirements and performance targets, the initial parameters of the needle loom are set, where the speed is set according to the fiber type, thickness, target output and matching of the production line equipment, the depth is set to 70%-80% of the fiber layer thickness, and the frequency is set according to the speed; Determine the reasonable fluctuation range of speed, depth and frequency, where the speed fluctuation range is within ±10%, the depth fluctuation range is within ±5%, and the frequency fluctuation is automatically adjusted according to the speed; Carry out small-batch trial production under set initial parameters to verify the rationality of parameter settings and analyze trial production data to determine the performance of felt fabrics.

3. The control method of a felt fabric production line according to claim 2, characterized in that: In step 2, the collection and preprocessing of raw data includes: Identify the acupuncture machine equipment parameters and environmental parameters that need to be collected, including speed, depth, frequency, temperature and humidity, and deploy sensors at corresponding locations; Acquire raw data from sensors, including historical data (retrieved from databases, log files, and archived records) and real-time data (continuously collecting current equipment and environmental parameters); Monitor acupuncture speed, actual puncture depth and frequency data, and collect environmental parameters using temperature and humidity sensors; The collected equipment parameters and environmental parameters are preprocessed, including data cleaning, calibration and normalization, converting data of different dimensions and ranges to a unified scale, and storing the preprocessed data in the data warehouse.

4. The control method of a felt fabric production line according to claim 3, characterized in that: In step 3, the process of establishing the interference prediction model includes: Traverse the pre-processed equipment parameters and environmental parameter data of the needle loom, extract the historical equipment parameters, environmental parameters of the needle loom and the quality inspection data of the felt fabric in the corresponding time period from the historical data, and mark the abnormal points; Combined with historical data and abnormal points, the relationship between needle machine equipment parameters and felt fabric quality is analyzed, and the equipment characteristics and environmental characteristics that affect the quality are extracted to form equipment feature sets and environmental feature sets; Based on the equipment feature set data combined with the neural network model, an equipment control model is constructed to predict the future state of the acupuncture machine; based on the environmental feature set data combined with the decision tree model, an environmental interference model is constructed to analyze the impact of environmental factors on production quality; Combined with the equipment control model and equipment feature set data, the equipment control index is analyzed to predict the change trend of the speed, depth and frequency of the needle machine; combined with the environmental interference model and environmental feature set data, the environmental interference index is obtained to analyze its impact on production quality; Extract the correlation data of equipment control index and environmental interference index, use historical data for model training, build an interference prediction model, and combine the index with the interference prediction model to obtain the abnormal fluctuation coefficient, predict the abnormalities and fluctuations in the production process, and analyze the quality abnormality risk under the joint action of equipment and environment.

5. The control method of a felt fabric production line according to claim 4, characterized in that: The expression of the device control index is: Where ECI is the equipment control index, n is the number of equipment parameters, and w i is the weight of the i-th parameter, the sum of the weights is 1, Ac i is the actual measured value of the i-th parameter, Base i is the reference value of the ith parameter, Trs i is the maximum allowable value of the reasonable fluctuation range of the i-th parameter, α is the adjustment coefficient, which is used to adjust the influence of the factor on ECI. The value range of ECI is 0 to 1. The smaller the ECI value, the better the equipment control and the more stable the production process. The expression of the environmental interference index is: Where EII is the environmental interference index, m is the number of environmental parameters, v j is the weight of the jth environmental parameter, the sum of the weights is 1, Env j is the actual measured value of the jth environmental parameter, Tar j is the target value of the jth environmental parameter, Tol j is the maximum allowable value of the reasonable fluctuation range of the jth environmental parameter, k is a constant used to adjust the sensitivity of the exponential function, and the value range of EII is from 0 to 1. The smaller the EII value, the better the environmental control and the more stable the production process.

6. The control method of a felt fabric production line according to claim 5, characterized in that: The expression of the abnormal fluctuation coefficient is: Among them, AFC is the abnormal fluctuation coefficient, n is the number of equipment parameters, m is the number of environmental parameters, and w i is the weight of the i-th device parameter, v j is the weight of the jth environmental parameter, ECI i is the equipment control index of the ith equipment parameter, EII j is the environmental interference index of the jth environmental parameter, x is a variable tending to infinity, which is used to adjust the limit behavior of the exponential function. The larger the AFC value, the higher the possibility of abnormalities and fluctuations in the production process.

7. The control method of a felt fabric production line according to claim 6, characterized in that: In step 4, the process of formulating the intelligent control strategy includes: According to the distribution of historical data and abnormal fluctuation coefficients, three abnormal fluctuation levels are set: low, medium, and high, and a fluctuation threshold range is corresponding to each level; According to different abnormal fluctuation levels, corresponding intelligent control strategies are formulated to automatically adjust the speed, depth and frequency of the acupuncture machine; Integrate intelligent control strategies into the control system of the felt fabric production line to achieve automated monitoring and adjustment, monitor production data and abnormal fluctuation coefficients, so as to accurately determine the current abnormal fluctuation level and take corresponding control measures.

8. The control method of a felt fabric production line according to claim 7, characterized in that: A plurality of the abnormal fluctuation levels correspond to a plurality of the fluctuation thresholds, wherein the fluctuation thresholds include an upper threshold and a lower threshold; The multiple abnormal fluctuation levels and the multiple fluctuation thresholds satisfy the following relationship: Low abnormal fluctuation level AFC≤AFC M ; Medium Abnormal Fluctuation Level AFC M <AFC≤AFC H ; High abnormal fluctuation level AFC>AFC H ; Among them, AFC is the abnormal volatility coefficient, AFC M is the upper threshold corresponding to the low abnormal fluctuation level and the lower threshold corresponding to the medium abnormal fluctuation level, AFC H The upper threshold corresponding to the medium abnormal fluctuation level and the lower threshold corresponding to the high abnormal fluctuation level.

9. The control method of a felt fabric production line according to claim 8, characterized in that: In step 5, the process of implementing the intelligent control strategy to control the acupuncture machine includes: Through the sensors installed in the needle loom and production environment, the equipment and environmental parameter data are collected in real time, and the real-time data is cleaned and preprocessed. The processed data is then input into the interference prediction model to analyze the current state of the needle loom and the parameter change trend; Calculate the abnormal fluctuation coefficient based on the model output, and combine it with the preset fluctuation threshold to determine the abnormal fluctuation level of the current production process; According to the determined fluctuation level, the corresponding intelligent control strategy is automatically executed, and the quality indicators of felt fabrics are continuously monitored, and the results are recorded in the data warehouse in real time; Set expected quality targets for felt fabrics, compare actual monitoring indicators with expected targets to evaluate the stability of the production process and the consistency of product quality. If there are deviations, analyze the causes and adjust the control strategies.

10. A control system for a felt fabric production line, used to implement the control method for a felt fabric production line according to any one of claims 1 to 9, comprising a control center, characterized in that: The control center is communicatively connected with a data acquisition and processing module, an interference prediction module, an abnormality determination module, an intelligent control module, a quality monitoring module and an early warning notification module, wherein electrical signals are connected between the modules; The data acquisition and processing module is used to collect the equipment parameters of the needle-loom machine and the environmental parameters of the felt fabric production line through sensors, and pre-process the collected data; The interference prediction module uses historical data and real-time data to predict the future state and parameter change trend of the needling machine, and identifies potential production fluctuations and anomalies in advance; The abnormality determination module calculates the abnormal fluctuation coefficient according to the output of the interference prediction model and determines the current abnormal fluctuation level; The intelligent control module automatically executes a preset control strategy according to the abnormal fluctuation level; The quality monitoring module is used to continuously monitor the quality indicators of the felt fabric, and to record the monitoring results in real time and feed them back to the control center; The warning notification module sends a warning notification to the operator in a timely manner when an abnormality occurs or is about to occur in the production process. The notification content includes the type of abnormality, the scope of impact and the recommended response measures, helping the operator to quickly respond and handle the problem.

Images