A method and system for online monitoring of rubber accumulation in a four-roll calendering mill

Abstract

The present invention discloses an online monitoring method and system for the accumulation of rubber in a four-roll calendering mill, and relates to the technical field of equipment monitoring. The online monitoring method for the accumulation of rubber in a four-roll calendering mill can not only comprehensively monitor the operating status and abnormal conditions of the equipment, but also timely warn and make necessary interventions, thereby improving the safety, stability and efficiency of the production process, and directly reflecting the abnormal degree of equipment operation by generating the calculation result of the abnormal coefficient YXC. When YXC is compared with a preset threshold, a first comparison result can be quickly generated, providing a reliable basis for subsequent abnormal processing and early warning. By responding to and handling abnormal conditions in a timely manner, we can effectively reduce the risk of production interruption and ensure the continuity and safety of production.

Description

Technical Field

[0001] The invention relates to the technical field of equipment monitoring, and in particular to an online monitoring method and system for rubber accumulation in a four-roll calendering mixing mill. Background Art

[0002] Four-roller calendering mill is a kind of equipment used in rubber processing, mainly used for plasticating, refining and calendering rubber mixtures or other composite materials. It usually consists of two parallel rollers, which can be driven by a motor to rotate at a specific speed to mix and extrude the raw materials. Four-roller calendering mill is widely used in the rubber industry. It can effectively process rubber mixtures into uniform and well-plasticized materials for the manufacture of various rubber products, such as tires, seals, rubber tubes, etc.

[0003] Traditionally, the monitoring and control of the four-roll calender mill mainly relies on the operator's experience and periodic inspections. However, this method has the following significant shortcomings: First, manual inspections often fail to capture minor anomalies in the operation of the equipment in a timely manner, resulting in problems that may not be detected before they become serious; second, the operation relies on individual experience and subjective judgment, making it difficult to ensure the objectivity and consistency of the monitoring results; finally, the lack of real-time data support and automated early warning systems limits the response speed to potential risks and makes it impossible to effectively ensure production continuity and safety. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the deficiencies in the prior art, the present invention provides an online monitoring method for rubber accumulation in a four-roll calendering mill, which solves the problems mentioned in the above background technology.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented by the following technical scheme: an online monitoring method for rubber accumulation in a four-roll calendering mill, the specific steps are as follows;

[0008] S1. An integrated sensor with multifunctional measurement capability is installed at a key position of the four-roll calendering mill. The sensor group acquires multiple data of the mill and integrates them into a first data set.

[0009] S2. Using a transmission detection system, detect the data process transmitted by the sensor to obtain multiple data sets generated during the sensor transmission, and integrate them into a second data set;

[0010] S3, processing the received data, and integrating and calculating the first data set and the second data set through a data fusion algorithm, thereby generating an abnormal coefficient YXC;

[0011] S4, comparing the calculated abnormal coefficient YXC with the preset first threshold value Y to generate a first comparison result, and judging whether an abnormality occurs in the four-roll rolling mill according to the first comparison result, if the first comparison result is judged to be an abnormality, integrating the abnormal coefficient YXC with the preset first threshold value Y to generate an abnormal difference coefficient YLZ, and comparing the calculated abnormal difference coefficient YLZ with the preset second threshold value R to generate a second comparison result;

[0012] S5. Issue an alarm based on the second comparison result.

[0013] Preferably, in step S1, an integrated sensor with multifunctional measurement capability is installed at a key position of the four-roll calendering mill, the sensor group is started, and multiple data of the mill are collected in real time, and the data of different sensors are integrated into a unified first data set. The first data set includes an operating temperature value T, a pressure value P, a displacement distance value D, an operating speed value V, a rubber thickness value H, and an equipment vibration value Vb.

[0014] Preferably, in step S2, a transmission detection system is used to monitor the sensor data transmission process in real time. The transmission detection system summarizes and processes the monitored data to generate a second data set containing multiple data in the transmission process. The second data set includes a transmission rate TR, a transmission error rate ER, a signal strength SS, a delay time LT, data integrity DI, and a number of retransmissions RC.

[0015] Preferably, in step S3, the specific calculation formula of the abnormal coefficient YXC is as follows:

[0016] ;

[0017] Wherein: a1 and a2 are weight values, and the values ​​of a1 and a2 are adjusted and set by the user, S1 is the first stage value obtained by integrating and calculating the first data set, S2 is the second stage value obtained by integrating and calculating the second data set, X1 is the first corrected intervention value, X2 is the second corrected intervention value, which are respectively obtained by integrating and calculating the first data set and the second data set, and e is the base function.

[0018] Preferably, the first stage value S1 and the second stage value S2 are calculated and obtained by the following formulas respectively:

[0019] ;

[0020] ;

[0021] Wherein: b1, b2, b3, b4, c1, c2 and c3 are weight values, the values ​​of b1, b2, b3, b4, c1, c2 and c3 are adjusted and set by the user, T is the operating temperature value, P is the pressure value, D is the displacement distance value, V is the operating speed value, TR is the transmission rate, SS is the signal strength, and LT is the delay time.

[0022] Preferably, the first corrected intervention value X1 and the second corrected intervention value X2 are calculated and obtained by the following formulas:

[0023] ;

[0024] ;

[0025] Where: e is the base function, ln is the logarithmic function, H is the rubber thickness value, Vb is the equipment vibration value, DI is the data integrity, and RC is the number of retransmissions.

[0026] Preferably, in step S4, the first comparison result is specifically as follows:

[0027] when When , it means that there is no abnormality in the current device;

[0028] when When it is displayed, it means that the current device is abnormal and may be due to glue accumulation.

[0029] Preferably, in step S4, the abnormal difference coefficient YLZ is calculated by the following formula:

[0030] ;

[0031] Where: YCX is the abnormal coefficient, Y is the first threshold.

[0032] Preferably, the second comparison result is as follows:

[0033] when When it is on, it means that the current device has a level 1 abnormality, indicating that there is a slight buildup of glue in the current device, and a blue indicator light is used for alarm;

[0034] when When it is on, it means that the current device has a secondary abnormality, indicating that moderate glue accumulation has occurred in the current device, and a yellow indicator light is used for alarm;

[0035] when When the device is in the third level of abnormality, it means that there is severe glue accumulation in the device, and the red indicator light is used for alarm.

[0036] The present application also includes an online monitoring system for rubber accumulation in a four-roll calendering mill, the system comprising a first information collection unit, a second information collection unit, a data preprocessing unit, a calculation unit, a first analysis unit, a second analysis unit and an alarm unit;

[0037] First information acquisition unit: The first information acquisition unit is an integrated sensor with multifunctional measurement capability. The sensor group acquires multiple data of the mixing mill and integrates them into a first data set;

[0038] Second information acquisition unit: The second information acquisition unit is a transmission detection system, which detects the data process transmitted by the sensor to obtain multiple data sets generated during the sensor transmission and integrates them into a second data set;

[0039] Data preprocessing unit: processes the received data, including cleaning, repairing and dimensionless conversion;

[0040] Calculation unit: integrates and calculates the first data set and the second data set through a data fusion algorithm to generate anomaly coefficient YXC;

[0041] The first analysis unit compares the calculated abnormal coefficient YXC with a preset first threshold value Y to generate a first comparison result, and determines whether an abnormality occurs in the four-roll rolling mill according to the first comparison result;

[0042] The second analysis unit: if it is determined that the first comparison result is abnormal, the abnormal coefficient YXC is integrated and calculated with the preset first threshold value Y to generate an abnormal difference coefficient YLZ, and the calculated abnormal difference coefficient YLZ is compared with the preset second threshold value R to generate a second comparison result;

[0043] The alarm unit issues an alarm according to the second comparison result.

[0044] (III) Beneficial effects

[0045] The present invention provides a method for online monitoring of rubber accumulation in a four-roll calendering mill, which has the following beneficial effects:

[0046] 1. The online monitoring method for rubber accumulation of the four-roll calender mixing mill can not only comprehensively monitor the operating status and abnormal conditions of the equipment, but also provide timely warnings and make necessary interventions by installing integrated sensors, using transmission detection systems, data processing and fusion calculations, comparing and judging abnormal coefficients, and responding to alarms. This method improves the safety, stability, and efficiency of the production process.

[0047] 2. The four-roll calendering mill rubber accumulation online monitoring method directly reflects the abnormal degree of equipment operation by generating the calculation result of the abnormal coefficient YXC. When YXC is compared with the preset threshold, the first comparison result can be quickly generated, providing a reliable basis for subsequent abnormal processing and early warning. By responding to and handling abnormal situations in a timely manner, we can effectively reduce the risk of production interruption and ensure the continuity and safety of production. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 It is a schematic diagram of the steps of the method of the present invention.

[0049] Figure 2 It is a schematic diagram of the system flow of the present invention. DETAILED DESCRIPTION

[0050] 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 only 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 ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0051] Example 1

[0052] See also Figure 1 , a method for online monitoring of rubber accumulation in a four-roll calendering mill, the specific steps are as follows;

[0053] S1. An integrated sensor with multifunctional measurement capability is installed at a key position of the four-roll calendering mill. The sensor group acquires multiple data of the mill and integrates them into a first data set.

[0054] S2. Using a transmission detection system, detect the data process transmitted by the sensor to obtain multiple data sets generated during the sensor transmission, and integrate them into a second data set;

[0055] S3, processing the received data, and integrating and calculating the first data set and the second data set through a data fusion algorithm, thereby generating an abnormal coefficient YXC;

[0056] S4, comparing the calculated abnormal coefficient YXC with the preset first threshold value Y to generate a first comparison result, and judging whether an abnormality occurs in the four-roll rolling mill according to the first comparison result, if the first comparison result is judged to be an abnormality, integrating the abnormal coefficient YXC with the preset first threshold value Y to generate an abnormal difference coefficient YLZ, and comparing the calculated abnormal difference coefficient YLZ with the preset second threshold value R to generate a second comparison result;

[0057] S5. Issue an alarm based on the second comparison result.

[0058] In this embodiment: in step S1, installing integrated sensors with multifunctional measurement capabilities at key positions of the four-roll rolling mill is the first step of the method. These sensors can simultaneously obtain multiple key data of the mill, such as temperature, pressure, vibration, etc., and integrate these data into a first data set. Through this step, the method can monitor the operating status of the mill in real time and comprehensively, ensuring the comprehensiveness and accuracy of data collection.

[0059] In step S2, using a transmission detection system to detect the data process transmitted by the sensor is a key step to ensure that there is no error or loss in the data transmission process. This process can obtain multiple data sets generated during sensor transmission and integrate them into a second data set. Through this step, the method can ensure the integrity of data from the sensor to the data processing system, and further improve the reliability and real-time performance of the data.

[0060] In step S3, the received first data set and the second data set need to be integrated and calculated by data processing and data fusion algorithm. This step aims to extract effective information from massive data and generate abnormal coefficients YXC. Through data processing and fusion calculation, this method can realize efficient analysis of complex data and timely discover and diagnose abnormal conditions in equipment operation.

[0061] In step S4, the calculated abnormal coefficient YXC is compared with the preset first threshold value Y to generate a first comparison result. According to the first comparison result, it is determined whether an abnormality occurs in the four-roll rolling mill. If the abnormality is confirmed, the abnormal coefficient YXC is further integrated and calculated with the preset first threshold value Y to generate an abnormal difference coefficient YLZ. Then, the calculated abnormal difference coefficient YLZ is compared with the preset second threshold value R to generate a second comparison result.

[0062] In step S5, an alarm is processed according to the second comparison result. If the second comparison result indicates that the equipment is abnormal, the system will immediately trigger an alarm mechanism to notify relevant personnel to intervene and process in time to avoid further damage or production interruption.

[0063] By installing integrated sensors, using transmission detection systems, data processing and fusion calculations, comparing and judging abnormal coefficients, and responding to alarms, this method can not only comprehensively monitor the equipment operating status and abnormal conditions, but also provide timely warnings and make necessary interventions, thereby improving the safety, stability, and efficiency of the production process.

[0064] Example 2

[0065] See also Figure 1 In step S1, an integrated sensor with multifunctional measurement capability is installed at a key position of the four-roll calendering mill, and the sensor group is started to collect multiple data of the mill in real time, and the data of different sensors are integrated into a unified first data set. The first data set includes an operating temperature value T, a pressure value P, a displacement distance value D, an operating speed value V, a rubber thickness value H, and an equipment vibration value Vb.

[0066] In this embodiment, the integrated sensor realizes real-time monitoring and collection of the operating temperature value T, pressure value P, displacement distance value D, operating speed value V, rubber thickness value H and equipment vibration value Vb. This comprehensive data collection method is more comprehensive and accurate than the traditional single sensor monitoring, ensuring a comprehensive understanding of the equipment operation status.

[0067] Integrated sensors can achieve multifunctional measurements, which not only improves the accuracy of data collection, but also reduces the number of monitoring equipment and maintenance costs. This integrated monitoring system greatly simplifies the monitoring process, making the operation more convenient and efficient.

[0068] Integrating various key data into a unified first data set provides a solid foundation for subsequent data processing and analysis. By acquiring multiple data in real time, we can promptly discover and diagnose potential problems of equipment, improving the stability and reliability of equipment operation.

[0069] Example 3

[0070] See also Figure 1 In step S2, the transmission detection system is used to monitor the sensor data transmission process in real time. The transmission detection system summarizes and processes the monitored data to generate a second data set containing multiple data in the transmission process. The second data set includes the transmission rate TR, the transmission error rate ER, the signal strength SS, the delay time LT, the data integrity DI and the number of retransmissions RC.

[0071] In this embodiment: by real-time monitoring of the sensor data transmission process, we can promptly discover and correct any possible transmission errors or data loss. Detailed monitoring of the transmission rate TR, transmission error rate ER, signal strength SS, delay time LT, data integrity DI and number of retransmissions RC ensures the integrity and accuracy of the data, thereby improving the stability and reliability of the system.

[0072] The use of the transmission detection system makes data processing more efficient and accurate. Aggregating and processing multiple data during the transmission process helps the system to conduct a deeper analysis and understanding of sensor data. This precise data processing capability enables subsequent data fusion algorithms to operate based on real and accurate data, further improving the accuracy and timeliness of anomaly detection and early warning.

[0073] The generation of the second data set provides important support for the intelligent management of the system. Based on the detailed data generated by the transmission detection system, we can more accurately determine whether the equipment is operating normally, respond to and handle potential abnormal situations in a timely manner, and effectively ensure the continuity and stability of the production process.

[0074] Example 4

[0075] See also Figure 1 In step S3, the specific calculation formula of the abnormal coefficient YXC is as follows:

[0076] ;

[0077] Wherein: a1 and a2 are weight values, and the values ​​of a1 and a2 are adjusted and set by the user, S1 is the first stage value obtained by integrating and calculating the first data set, S2 is the second stage value obtained by integrating and calculating the second data set, X1 is the first corrected intervention value, X2 is the second corrected intervention value, which are respectively obtained by integrating and calculating the first data set and the second data set, and e is the base function.

[0078] In this embodiment, the S1 and S2 values ​​calculated by integrating the first data set and the second data set, combined with the modified intervention values ​​X1 and X2, can more accurately reflect the real-time changes in the operating status of the equipment. This comprehensive analysis based on multiple data improves the sensitivity and accuracy of anomaly detection, allowing the system to promptly discover and identify potential abnormal situations.

[0079] Through user-adjustable weight values ​​a1 and a2, we can adjust the influence of different parameters on the abnormal coefficient according to actual conditions, so as to customize the monitoring system to meet specific production needs and safety standards. This flexibility and adjustability helps to optimize the monitoring strategy and improve the adaptability of the system.

[0080] The calculation result of the abnormal coefficient YXC directly reflects the abnormal degree of equipment operation. When YXC is compared with the preset threshold, the first comparison result can be quickly generated, providing a reliable basis for subsequent abnormal processing and early warning. By responding and handling abnormal situations in a timely manner, we can effectively reduce the risk of production interruption and ensure the continuity and safety of production.

[0081] Example 5

[0082] See also Figure 1 , the first stage value S1 and the second stage value S2 are calculated and obtained by the following formulas respectively;

[0083] ;

[0084] ;

[0085] Wherein: b1, b2, b3, b4, c1, c2 and c3 are weight values, the values ​​of b1, b2, b3, b4, c1, c2 and c3 are adjusted and set by the user, T is the operating temperature value, P is the pressure value, D is the displacement distance value, V is the operating speed value, TR is the transmission rate, SS is the signal strength, and LT is the delay time.

[0086] In this embodiment: the first stage value S1 utilizes the square of the operating temperature T, the square root of the pressure P, the natural logarithm of the displacement distance D, and the square of the operating speed V. These calculations can more comprehensively reflect the various physical changes of the equipment during operation. This multi-parameter comprehensive calculation improves the detailed monitoring of the equipment status, helps to timely discover and analyze possible abnormal situations, and thus reduces the risk of production interruption caused by equipment failure.

[0087] The second stage value S2 uses the logarithm of the transmission rate TR, the square of the signal strength SS, and the inverse of the delay time LT. The comprehensive analysis of these parameters can effectively reflect the stability and real-time performance of the data transmission process. Through comprehensive monitoring and analysis of the transmission process, the system can promptly detect data transmission anomalies, ensure the accuracy and integrity of the monitoring data, and thus improve the efficiency and accuracy of production data processing.

[0088] The adjustability of weight values ​​b1, b2, b3, b4, c1, c2 and c3 enables users to adjust the influence of different parameters on S1 and S2 according to specific needs. This flexibility allows the monitoring system to be customized according to specific production environments and process requirements, optimize monitoring strategies, and improve the adaptability and responsiveness of the system.

[0089] Combined with the integrated calculation of the first data set and the second data set, the first stage value S1 and the second stage value S2 calculated by the formula can more accurately evaluate the real-time changes in the equipment operation status and the stability of the transmission process. This enhanced anomaly detection and early warning mechanism helps to timely discover potential equipment anomalies and take preventive measures to avoid possible production losses and safety risks.

[0090] Example 6

[0091] See also Figure 1 The first corrected intervention value X1 and the second corrected intervention value X2 are calculated and obtained by the following formulas:

[0092] ;

[0093] ;

[0094] Where: e is the base function, ln is the logarithmic function, H is the rubber thickness value, Vb is the equipment vibration value, DI is the data integrity, and RC is the number of retransmissions.

[0095] In this embodiment: the first corrected intervention value X1 utilizes the square of the rubber thickness H and the logarithmic processing of the equipment vibration Vb. These parameters can more carefully reflect the physical state of the equipment during operation. Through this comprehensive evaluation, the system can more accurately determine whether the equipment is within the normal working range, which helps to prevent possible failures and downtime in advance, thereby reducing the risk of production interruption.

[0096] The second corrected intervention value X2 uses the square root of data integrity DI and the logarithm of the number of retransmissions RC, combined with the exponential processing of the transmission error rate ER. These calculations can effectively evaluate the stability and integrity of the data transmission process. Through in-depth analysis of the data transmission process, the system can promptly discover and correct possible problems in data transmission, ensure the reliability and integrity of monitoring data, and improve the efficiency and accuracy of production data processing.

[0097] The base and logarithmic function in the formula provide flexibility, allowing users to adjust the weights and calculation methods of X1 and X2 according to specific production environments and monitoring requirements. This flexibility enables the monitoring system to better adapt to different process and operating conditions, optimize monitoring strategies, and improve system stability and operability.

[0098] The X1 and X2 values ​​calculated comprehensively can more accurately assess the equipment status and data transmission stability. This enhanced monitoring and evaluation capability helps to promptly detect potential equipment anomalies and data transmission problems, take preventive measures and adjustments, and minimize risks and losses in production.

[0099] Example 7

[0100] See also Figure 1 , in step S4, the first comparison result is as follows;

[0101] when When , it means that there is no abnormality in the current device;

[0102] when When it is displayed, it means that the current device is abnormal and may be due to glue accumulation.

[0103] In step S4, the abnormal difference coefficient YLZ is calculated by the following formula:

[0104] ;

[0105] Where: YCX is the abnormal coefficient, Y is the first threshold.

[0106] The second comparison results are as follows:

[0107] when When it is on, it means that the current device has a level 1 abnormality, indicating that there is a slight buildup of glue in the current device, and a blue indicator light is used for alarm;

[0108] when When it is on, it means that the current device has a secondary abnormality, indicating that moderate glue accumulation has occurred in the current device, and a yellow indicator light is used for alarm;

[0109] when , it means that the current device has a level 3 abnormality, indicating that there is severe glue accumulation in the current device, and a red indicator light is used for alarm.

[0110] In this embodiment: by comparing YXC and the preset threshold value Y, real-time monitoring and abnormality detection of the device status can be achieved. At any time, the system determines that the equipment is operating normally and does not require further intervention or maintenance, which effectively saves the time and cost of maintenance personnel and ensures the continuity and stability of production. At any time, the system can automatically trigger further exception handling processes. This automated processing capability can quickly respond to possible equipment problems and take appropriate measures, such as notifying maintenance personnel to perform maintenance or adjust production strategies, thereby minimizing the impact of equipment failures on production. With the help of the first comparison results, production managers can understand the equipment operating status more promptly, handle potential abnormal situations in a timely manner, and ensure the safety and stability of the production process. This real-time monitoring and response capability helps reduce the risk of production interruptions and improve the reliability and service life of equipment.

[0111] By comparing the abnormal difference coefficient YLZ with the preset threshold R, the system can finely classify and respond to abnormalities in the equipment. According to different YLZ values, the system uses different alarm signals such as blue and yellow indicator lights to accurately reflect the severity of the equipment's operating status and help operators quickly identify and deal with problems.

[0112] when When the system triggers a level 1 abnormal alarm, the blue indicator light is used to prompt the operator to pay attention and take necessary operation or maintenance measures to avoid further deterioration of the problem. This rapid response capability effectively reduces the potential impact of equipment failure on production and improves production efficiency and operational stability.

[0113] when When the system detects a secondary abnormality, it uses a yellow indicator light to sound an alarm. This early warning capability helps production managers take preventive measures and make adjustments before a problem occurs, effectively reducing the frequency of emergencies and improving production safety and reliability.

[0114] when When the system is in a state of emergency, the system will issue a three-level abnormal alarm and use a red indicator light to prompt. At this time, the operator can respond quickly and perform emergency shutdown or other necessary operations to minimize production downtime and losses. This immediate abnormal response mechanism helps to improve the operability of the equipment and the continuity of the production process.

[0115] The present application also includes an online monitoring system for rubber accumulation in a four-roll calendering mill, the system comprising a first information collection unit, a second information collection unit, a data preprocessing unit, a calculation unit, a first analysis unit, a second analysis unit and an alarm unit;

[0116] First information acquisition unit: The first information acquisition unit is an integrated sensor with multifunctional measurement capability. The sensor group acquires multiple data of the mixing mill and integrates them into a first data set;

[0117] Second information acquisition unit: The second information acquisition unit is a transmission detection system, which detects the data process transmitted by the sensor to obtain multiple data sets generated during the sensor transmission and integrates them into a second data set;

[0118] Data preprocessing unit: processes the received data, including cleaning, repairing and dimensionless conversion;

[0119] Calculation unit: integrates and calculates the first data set and the second data set through a data fusion algorithm to generate anomaly coefficient YXC;

[0120] The first analysis unit compares the calculated abnormal coefficient YXC with a preset first threshold value Y to generate a first comparison result, and determines whether an abnormality occurs in the four-roll rolling mill according to the first comparison result;

[0121] The second analysis unit: if it is determined that the first comparison result is abnormal, the abnormal coefficient YXC is integrated and calculated with the preset first threshold value Y to generate an abnormal difference coefficient YLZ, and the calculated abnormal difference coefficient YLZ is compared with the preset second threshold value R to generate a second comparison result;

[0122] The alarm unit issues an alarm according to the second comparison result.

[0123] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for online monitoring of rubber accumulation in a four-roll calendering mill, characterized in that: The specific steps are as follows; S1. An integrated sensor with multifunctional measurement capability is installed at a key position of the four-roll calendering mill. The sensor group acquires multiple data of the mill and integrates them into a first data set. An integrated sensor with multifunctional measurement capability is installed at a key position of the four-roll calendering mill, and the sensor group is started to collect multiple data of the mill in real time, and the data of different sensors are integrated into a unified first data set, which includes the operating temperature value T, the pressure value P, the displacement distance value D, the operating speed value V, the rubber thickness value H and the equipment vibration value Vb; S2. Using a transmission detection system, detect the data process transmitted by the sensor to obtain multiple data sets generated during the sensor transmission, and integrate them into a second data set; A transmission detection system is used to monitor the sensor data transmission process in real time. The transmission detection system aggregates and processes the monitored data to generate a second data set containing multiple data in the transmission process. The second data set includes a transmission rate TR, a signal strength SS, a delay time LT, a data integrity DI, and a retransmission count RC; S3, processing the received data, and integrating and calculating the first data set and the second data set through a data fusion algorithm, thereby generating an abnormal coefficient YXC; The specific calculation formula of the abnormal coefficient YXC is as follows: ； Where: a1 and a2 are weight values, and the values ​​of a1 and a2 are adjusted and set by the user, S1 is the first stage value obtained by integrating the first data set, S2 is the second stage value obtained by integrating the second data set, X1 is the first corrected intervention value, X2 is the second corrected intervention value, which are obtained by integrating the first data set and the second data set, respectively, and e is the base function; The first stage value S1 and the second stage value S2 are calculated and obtained by the following formulas respectively; ； ； Wherein: b1, b2, b3, b4, c1, c2 and c3 are weight values, the values ​​of b1, b2, b3, b4, c1, c2 and c3 are adjusted and set by the user, T is the operating temperature value, P is the pressure value, D is the displacement distance value, V is the operating speed value, TR is the transmission rate, SS is the signal strength, and LT is the delay time; The first corrected intervention value X1 and the second corrected intervention value X2 are calculated by the following formulas: ； ； In the formula: e is the base function, ln is the logarithmic function, H is the rubber thickness value, Vb is the equipment vibration value, DI is the data integrity, and RC is the number of retransmissions; S4, comparing the calculated abnormal coefficient YXC with the preset first threshold value Y to generate a first comparison result, and judging whether an abnormality occurs in the four-roll rolling mill according to the first comparison result, if the first comparison result is judged to be an abnormality, integrating the abnormal coefficient YXC with the preset first threshold value Y to generate an abnormal difference coefficient YLZ, and comparing the calculated abnormal difference coefficient YLZ with the preset second threshold value R to generate a second comparison result; The first comparison results are as follows: when When , it means that there is no abnormality in the current device; when When it is displayed, it means that the current device is abnormal and may be prone to glue accumulation. In step S4, the second comparison result is as follows: when When it is on, it means that the current device has a level 1 abnormality, indicating that there is a slight buildup of glue in the current device, and a blue indicator light is used for alarm; when When it is on, it means that the current device has a secondary abnormality, indicating that moderate glue accumulation has occurred in the current device, and a yellow indicator light is used for alarm; when When it is on, it means that the current device has a level 3 abnormality, which means that there is severe glue accumulation in the current device, and a red indicator light is used for alarm; The abnormal difference coefficient YLZ is calculated by the following formula: ； Where: YCX is the abnormal coefficient, Y is the first threshold; S5. Issue an alarm based on the second comparison result.

2. An online monitoring system for rubber accumulation of a four-roll calendering mill, characterized in that: The system is used to implement the online monitoring method for rubber accumulation in a four-roll calendering mill according to any one of the above claims 1, and the system comprises a first information collection unit, a second information collection unit, a data preprocessing unit, a calculation unit, a first analysis unit, a second analysis unit and an alarm unit; First information acquisition unit: The first information acquisition unit is an integrated sensor with multifunctional measurement capability. The sensor group acquires multiple data of the mixing mill and integrates them into a first data set; Second information acquisition unit: The second information acquisition unit is a transmission detection system, which detects the data process transmitted by the sensor to obtain multiple data sets generated during the sensor transmission and integrates them into a second data set; Data preprocessing unit: processes the received data, including cleaning, repairing and dimensionless conversion; Calculation unit: integrates and calculates the first data set and the second data set through a data fusion algorithm to generate anomaly coefficient YXC; The first analysis unit compares the calculated abnormal coefficient YXC with a preset first threshold value Y to generate a first comparison result, and determines whether an abnormality occurs in the four-roll rolling mill according to the first comparison result; The second analysis unit: if it is determined that the first comparison result is abnormal, the abnormal coefficient YXC is integrated and calculated with the preset first threshold value Y to generate an abnormal difference coefficient YLZ, and the calculated abnormal difference coefficient YLZ is compared with the preset second threshold value R to generate a second comparison result; The alarm unit issues an alarm according to the second comparison result.

Images