A flexible production conveyor belt dynamic speed regulation intelligent matching system

Abstract

This invention discloses a dynamic speed regulation intelligent matching system for flexible production conveyor belts, relating to the field of conveyor belt speed regulation technology. The matching system includes: a conveying data analysis module, used to collect data for each conveying process of the conveyor belt and generate a conveying log; identify congestion behaviors in any conveying log to obtain a set of congestion behaviors; a congestion feature analysis module, used to compare the differences of various congestion behaviors and classify them; identify abnormal features of congestion behaviors; a conveying prediction decision module, used to construct a congestion prediction model to predict the congestion situation of the conveying log; formulate corresponding adjustment decisions for various congestion behaviors; and a real-time prediction feedback module, used to monitor the real-time conveying process on the conveyor belt, obtain a real-time conveying log, predict congestion in the real-time conveying log and make timely adjustments; identify and alert to any abnormal situations after adjustment.

Description

Technical Field

[0001] This invention relates to the field of conveyor belt speed control technology, specifically a dynamic speed control intelligent matching system for flexible production conveyor belts. Background Technology

[0002] Flexible production conveyor belts are intelligent material handling equipment used in modern intelligent manufacturing systems. Their core design goal is to adapt to the production needs of multiple varieties, small batches, and rapid production changeover. By dynamically adjusting speed, path, and operating mode, they maximize the flexibility and efficiency of the production process.

[0003] Traditional conveyor belt systems often employ fixed speed regulation or speed regulation strategies based on simple rules, such as preset speed curves. These strategies cannot adapt to dynamic changes in the production environment in real time. The system struggles to adjust the conveying speed quickly, resulting in significant feedback delays and untimely speed regulation responses, which negatively impacts production efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide a dynamic speed regulation intelligent matching system for flexible production conveyor belts to solve the problems raised in the prior art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: a dynamic speed regulation intelligent matching system for flexible production conveyor belts, the matching system comprising a conveying data analysis module, a congestion feature analysis module, a conveying prediction decision module, and a real-time prediction feedback module;

[0006] The conveyor data analysis module is used to collect data on each conveying process of the conveyor belt through preset monitoring equipment and generate a conveyor log; it identifies congestion behaviors in any conveyor log and obtains a set of congestion behaviors for any conveyor log.

[0007] The congestion feature analysis module is used to compare the differences between various congestion behaviors in all congestion behavior sets, classify different congestion behaviors into categories, identify abnormal features of any type of congestion behavior, and analyze the feature range of each abnormal feature.

[0008] The delivery prediction and decision-making module is used to build a congestion prediction model to predict the congestion situation of delivery logs and to train it based on the actual congestion situation of any delivery log; and to make corresponding adjustment decisions for various congestion behaviors based on the prediction results.

[0009] The real-time prediction and feedback module is used to monitor the real-time conveying process on the conveyor belt, obtain real-time conveying logs, predict congestion based on the real-time conveying logs and make timely adjustments; monitor changes in abnormal characteristics after adjustment, identify existing abnormalities and issue alerts.

[0010] Furthermore, the transport data analysis module includes a transport log collection unit and a transport congestion identification unit;

[0011] The conveyor log collection unit is used to divide the conveyor belt into several conveying areas according to preset functional types, and each conveying area is equipped with corresponding monitoring equipment. Whenever the conveyor belt starts conveying, each monitoring device starts to collect conveying data from the corresponding conveying area until the conveyor belt stops conveying. The monitoring data collected during each complete conveying process is presented according to the monitoring time to show the data changes, resulting in a corresponding conveying log. The conveyor belt can be divided into multiple conveying areas such as handling section, sorting section, and buffer section according to functional types, and each conveying area is equipped with monitoring equipment such as pressure sensors, speed sensors, and monitors to collect data on the conveying process.

[0012] The transport congestion identification unit is used to arbitrarily select a transport log, arbitrarily select a monitoring device from the selected transport log, extract the monitoring data of the monitoring device at any monitoring time point, and set the monitoring data detected by each monitoring device as a type of monitoring data. A normal value range is preset for each type of monitoring data. Specifically, a normal value range r=(d1,d2) is preset for the selected monitoring device, where d1 is the minimum value and d2 is the maximum value. The value of the monitoring data at monitoring time point t0 is set as d. t0 ,like Then, several consecutive monitoring time points adjacent to the monitoring time point t0 are obtained. If the values ​​of the monitoring data at these several monitoring time points are not within the normal range, the several monitoring time points are merged to obtain a time interval, and the conveying behavior within the time interval is obtained to obtain a congestion behavior in the conveying log. The congestion behavior in each time interval is obtained to obtain a set of congestion behaviors in the selected conveying log. The conveyor belt will generate data fluctuations during the conveying process, so the monitoring data at only one time point cannot accurately reflect whether there is congestion behavior. Only when there are anomalies in a continuous time interval can it be identified as congestion behavior.

[0013] Furthermore, the congestion feature analysis module includes a transportation congestion segmentation unit and an anomaly feature identification unit;

[0014] The delivery congestion segmentation unit is used to select any congested behavior from a delivery log, acquire the time interval and various monitoring data of the selected congested behavior, compare the differences in the time interval and monitoring data between any two congested behaviors, and determine whether to classify the two user behaviors.

[0015] The abnormal feature identification unit is used to analyze the abnormal situations of any congestion behavior in various types of monitoring data within any category of the same type, and extract several abnormal features; and to extract the monitoring data corresponding to any abnormal feature in different congestion behaviors to obtain the feature value range of any abnormal feature.

[0016] Furthermore, the transport congestion segmentation unit includes:

[0017] Arbitrarily select a delivery log, and arbitrarily select a congestion behavior from that delivery log. Set the selected congestion behavior as the target congestion behavior, and obtain the time interval of the target congestion behavior as (t). g1 ,t g2 );

[0018] Obtain the conveying speed of the conveyor belt in each conveying zone, and obtain the expected time interval for each conveying zone. The expected time interval for the i-th conveying zone is set as (t1...). i ,t2 i If (t) g1 ,t g2 )∈(t1 i ,t2 i If the expected occurrence area of ​​the target congestion behavior is obtained as the i-th transport area, and the actual occurrence area of ​​the target congestion behavior is captured by the monitoring equipment as the a-th transport area, a transport deviation flag F is set. If i ≠ a, then a first deviation flag F is set. (i,a) Make F=F (i,a) If i=a, then set the second deviation flag F. i Make F=F i The first deviation marker indicates that the congestion caused by congestion behavior has resulted in the congestion of the transported products in other transport areas, indicating that the transport process is obstructed; the second deviation marker indicates the congestion situation in a transport area; since different transport areas have different functions, the congestion behavior in different areas is different, so the congestion behavior can be judged by the different congestion areas to determine whether the congestion behavior is the same type of behavior.

[0019] The monitoring data of any selected monitoring device changes over time. The normal value range of the selected monitoring device is obtained. If the monitoring value at any monitoring time point in a continuous time interval does not belong to the normal value range, the selected monitoring device is marked as abnormal, and the set A of monitoring devices with abnormal markings in the target congestion behavior is obtained.

[0020] Select another congestion behavior from the remaining congestion behaviors and set it as the comparison congestion behavior, then obtain the transport deviation flag F of the comparison congestion behavior. ’ and the collection A of all monitoring devices containing anomaly markers’ If F ’ =F and A=A ’ If the target congestion behavior and the comparison congestion behavior are classified as similar congestion behaviors, then they are classified as different congestion behaviors.

[0021] Furthermore, the anomaly feature recognition unit includes:

[0022] Select any group of similar congestion behaviors and extract the set of monitoring devices with anomaly markers within that group. From this set, randomly select one monitoring device and obtain its monitoring data from all transport logs, thus obtaining a complete numerical range (d). min ,d max The normal value range of the monitoring equipment is set to (d1, d2). If d1 > d2, then... min Then we get a deviation range p1=(d min ,d1), if d2 < d max Then we get a deviation range p2=(d2,d max );

[0023] If the selected monitoring equipment has a deviation range, the data type of the monitoring data is set to the abnormal features of the selected monitoring equipment; the abnormal features of each monitoring equipment in each transmission log containing the same type of congestion behavior are extracted to obtain several abnormal features of the same type of congestion behavior.

[0024] By arbitrarily selecting an anomaly feature, and acquiring the transport logs of any congestion behavior within the same type of congestion behavior, the range of deviation values ​​(d1) of the monitoring equipment containing the selected anomaly feature is obtained. ’ ,d2 ’ If d1 ’ <d2<d2 ’ Then the actual deviation range of the corresponding delivery log is (d2, d2) ’ The actual deviation range of each congestion behavior in the same type of congestion behavior is extracted and the intersection is taken to obtain the feature value range of the selected abnormal features. There are multiple congestion behaviors in the same transport area, which are caused by various reasons. Therefore, the deviation of monitoring data caused by different congestion behaviors is different. In order to distinguish different congestion behaviors, the deviation needs to be further subdivided to better provide reference data for subsequent prediction models.

[0025] Furthermore, the delivery prediction and decision-making module includes a prediction model building unit and an adjustment decision-making unit;

[0026] The prediction model building unit is used to arbitrarily select a delivery log, analyze the deviation of abnormal features contained in any delivery area in the selected delivery log, analyze the frequency of abnormal occurrence of each abnormal feature, obtain the abnormal weight of each abnormal feature, build a congestion prediction model to predict the congestion risk of each delivery area; and obtain the risk prediction threshold for judging whether there is congestion behavior in each delivery area by the actual congestion situation of each delivery log in each delivery area.

[0027] The adjustment decision-making unit is used to extract abnormal features from any transport area in the transport log where the congestion risk value exceeds the risk prediction threshold, adjust the monitoring data corresponding to any abnormal feature, and generate an adjustment decision.

[0028] Furthermore, the predictive model building blocks include:

[0029] From the selected transport logs, arbitrarily select a transport region and obtain several abnormal features contained within that region. Calculate the feature value range for each abnormal feature, where the feature value range of the j-th abnormal feature in the transport region is set to [d]. j (min),d j [(max)]; Obtain the normal numerical range (d1) of the j-th abnormal feature. j ,d2 j Let a feature deviation value Q be assigned to the j-th anomalous feature. j If d j (max) < d1 j Then Q j =d j (max), if d2 j <d j (min), then Q j =d j (min); the deviation amplitude of the j-th abnormal feature is obtained as η. j =[Min(|Q j -d1 j |,|Q j -d2 j |)] / [Select(d1 j ,d2 j ]], where Min() is the minimum value function and Select() is the selection function. If the minimum value function obtains |Q j -d1 j |, then Select(d1) j ,d2 j )=d1 j If we take the minimum value of the function, we get |Q j -d2 j|, then Select(d1) j ,d2 j )=d2 j The value with the smallest deviation is selected as the basis for risk prediction because congestion will occur if no adjustments are made after the deviation is minimized.

[0030] The number of times the j-th anomaly occurs in all delivery logs is m. j The number of behaviors containing the j-th anomalous feature among all congestion behaviors is n. j The anomaly weight f of the j-th anomalous feature is calculated. j =n j / m j ;

[0031] Congestion prediction model is constructed to calculate the predicted congestion risk value R for the transport area. ex :

[0032] ;

[0033] Where b represents the number of abnormal features in the transport area; if congestion occurs in the selected transport area from the selected transport logs, then the congestion risk prediction value R is... ex Set as the abnormal prediction value; obtain the abnormal prediction value of any congestion behavior in the transportation area, and select the abnormal prediction value with the smallest value as the risk prediction threshold for judging whether there is congestion behavior in the transportation area.

[0034] Furthermore, adjustments will be made to the decision-making units, including:

[0035] Set the risk prediction threshold as R th Select a transport region from any transport log. If the predicted congestion risk value obtained for the selected transport region is R... ex If R ex ≥R th Then, all abnormal features contained in the selected transport area are extracted;

[0036] The system identifies the monitoring equipment containing any abnormal feature, formulates an adjustment plan to adjust the conveyor belt in the selected conveying area, and ensures that the monitoring data of the monitoring equipment is within the normal range. It also formulates corresponding adjustment plans for all abnormal features and generates an adjustment decision for the selected conveying area.

[0037] Furthermore, the real-time prediction feedback module includes a real-time delivery prediction unit and an abnormal congestion feedback unit;

[0038] The real-time delivery prediction unit is used to acquire monitoring data from various monitoring devices in the real-time delivery log, obtain the monitoring data of any monitoring device at the current monitoring time point, and if the monitoring data at the current monitoring time point does not belong to the preset normal value range, then it extracts abnormal features from the monitoring devices and obtains the deviation amplitude η of the monitoring data. now The abnormal weight f of the extracted abnormal features is obtained; the abnormal weight of each abnormal feature in any transport area and the deviation of the corresponding monitoring data are obtained and input into the congestion prediction model to obtain the congestion risk prediction value of each transport area in the real-time transport log; and the transport areas whose congestion risk prediction value exceeds the risk prediction threshold are adjusted.

[0039] The abnormal congestion feedback unit is used to acquire the monitoring data of each monitoring device in the adjusted transport area at regular intervals. If the monitoring data of a monitoring device is not within the normal value range for several consecutive monitoring time points, an abnormality reminder is sent to the adjusted transport area.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] 1. This invention analyzes the congestion behavior of conveyor belts during the conveying process, constructs a predictive model to predict congestion at any given time, helps to adjust the conveying speed of the conveyor belt in each stage in a timely manner, avoids the occurrence of untimely speed adjustment response, and effectively improves production efficiency.

[0042] 2. This invention categorizes and analyzes congestion behaviors in historical transport logs, sets identification methods for different categories of congestion behaviors, and can promptly capture potential congestion situations during transport, providing timely feedback and helping staff to make timely corrections.

[0043] 3. By formulating corresponding adjustment strategies for the conveyor belt, this invention can adapt well to the dynamic changes brought about by the production environment. It enables the conveyor belt to quickly make feedback adjustments when congestion anomalies are detected at any time, thus avoiding interruption of the production process. Attached Figure Description

[0044] Figure 1 This is a schematic diagram of a flexible production conveyor belt dynamic speed regulation intelligent matching system. Detailed Implementation

[0045] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0046] Example: Figure 1 As shown, the present invention provides a dynamic speed regulation intelligent matching system for flexible production conveyor belts. The matching system includes a conveying data analysis module, a congestion feature analysis module, a conveying prediction decision module, and a real-time prediction feedback module.

[0047] The conveyor data analysis module is used to collect data on each conveying process of the conveyor belt through preset monitoring equipment and generate a conveyor log; it identifies congestion behaviors in any conveyor log and obtains a set of congestion behaviors for any conveyor log.

[0048] The transportation data analysis module includes a transportation log collection unit and a transportation congestion identification unit.

[0049] The conveyor log collection unit is used to divide the conveyor belt into several conveying areas according to preset functional types, and each conveying area is equipped with corresponding monitoring equipment. Whenever the conveyor belt starts conveying, each monitoring device starts to collect conveying data of the corresponding conveying area until the conveyor belt stops conveying. The monitoring data collected during each complete conveying process is presented according to the monitoring time to show the data changes, thus obtaining the corresponding conveying log.

[0050] The transport congestion identification unit is used to arbitrarily select a transport log, arbitrarily select a monitoring device from the selected transport log, extract the monitoring data of the monitoring device at any monitoring time point, and set the monitoring data detected by each monitoring device as a type of monitoring data. A normal value range is preset for each type of monitoring data. Specifically, a normal value range r=(d1,d2) is preset for the selected monitoring device, where d1 is the minimum value and d2 is the maximum value. The value of the monitoring data at monitoring time point t0 is set as d. t0 ,like Then, obtain several monitoring time points that are adjacent to and consecutive to the monitoring time point t0. If the values ​​of the monitoring data under the several monitoring time points are not within the normal value range, then merge the several monitoring time points to obtain a time interval, and obtain the transmission behavior in the time interval to obtain a congestion behavior of the transmission log; obtain the congestion behavior of each time interval to obtain the set of congestion behaviors of the selected transmission log.

[0051] The congestion feature analysis module is used to compare the differences between various congestion behaviors in all congestion behavior sets, classify different congestion behaviors into categories, identify abnormal features of any type of congestion behavior, and analyze the feature range of each abnormal feature.

[0052] The congestion feature analysis module includes a transportation congestion division unit and an abnormal feature identification unit.

[0053] The delivery congestion segmentation unit is used to select any congested behavior from a delivery log, acquire the time interval and various monitoring data of the selected congested behavior, compare the differences in the time interval and monitoring data between any two congested behaviors, and determine whether to classify the two user behaviors.

[0054] The abnormal feature identification unit is used to analyze the abnormal situations of any congestion behavior in various types of monitoring data within any category of the same type, and extract several abnormal features; and to extract the monitoring data corresponding to any abnormal feature in different congestion behaviors to obtain the feature value range of any abnormal feature.

[0055] The transportation congestion division unit includes:

[0056] Arbitrarily select a delivery log, and arbitrarily select a congestion behavior from that delivery log. Set the selected congestion behavior as the target congestion behavior, and obtain the time interval of the target congestion behavior as (t). g1 ,t g2 );

[0057] Obtain the conveying speed of the conveyor belt in each conveying zone, and obtain the expected time interval for each conveying zone. The expected time interval for the i-th conveying zone is set as (t1...). i ,t2 i If (t) g1 ,t g2 )∈(t1 i ,t2 i If the expected occurrence area of ​​the target congestion behavior is obtained as the i-th transport area, and the actual occurrence area of ​​the target congestion behavior is captured by the monitoring equipment as the a-th transport area, a transport deviation flag F is set. If i ≠ a, then a first deviation flag F is set. (i,a) Make F=F (i,a) If i=a, then set the second deviation flag F. i Make F=F i ;

[0058] The monitoring data of any selected monitoring device changes over time. The normal value range of the selected monitoring device is obtained. If the monitoring value at any monitoring time point in a continuous time interval does not belong to the normal value range, the selected monitoring device is marked as abnormal, and the set A of monitoring devices with abnormal markings in the target congestion behavior is obtained.

[0059] Select another congestion behavior from the remaining congestion behaviors and set it as the comparison congestion behavior, then obtain the transport deviation flag F of the comparison congestion behavior. ’ and the collection A of all monitoring devices containing anomaly markers ’ If F ’ =F and A=A ’ If the target congestion behavior and the comparison congestion behavior are classified as similar congestion behaviors, then they are classified as different congestion behaviors.

[0060] The anomaly feature recognition unit includes:

[0061] Select any group of similar congestion behaviors and extract the set of monitoring devices with anomaly markers within that group. From this set, randomly select one monitoring device and obtain its monitoring data from all transport logs, thus obtaining a complete numerical range (d). min ,d max The normal value range of the monitoring equipment is set to (d1, d2). If d1 > d2, then... min Then we get a deviation range p1=(d min ,d1), if d2 < d max Then we get a deviation range p2=(d2,d max );

[0062] If the selected monitoring equipment has a deviation range, the data type of the monitoring data is set to the abnormal features of the selected monitoring equipment; the abnormal features of each monitoring equipment in each transmission log containing the same type of congestion behavior are extracted to obtain several abnormal features of the same type of congestion behavior.

[0063] By arbitrarily selecting an anomaly feature, and acquiring the transport logs of any congestion behavior within the same type of congestion behavior, the range of deviation values ​​(d1) of the monitoring equipment containing the selected anomaly feature is obtained. ’ ,d2 ’ If d1 ’ <d2<d2 ’ Then the actual deviation range of the corresponding delivery log is (d2, d2) ’ Extract the actual deviation range of each congestion behavior in the same type of congestion behavior and take the intersection to obtain the feature value range of the selected abnormal features.

[0064] The delivery prediction and decision-making module is used to build a congestion prediction model to predict the congestion situation of delivery logs and to train it based on the actual congestion situation of any delivery log; and to make corresponding adjustment decisions for various congestion behaviors based on the prediction results.

[0065] The delivery prediction and decision-making module includes a prediction model building unit and an adjustment decision-making unit.

[0066] The prediction model building unit is used to arbitrarily select a delivery log, analyze the deviation of abnormal features contained in any delivery area in the selected delivery log, analyze the frequency of abnormal occurrence of each abnormal feature, obtain the abnormal weight of each abnormal feature, build a congestion prediction model to predict the congestion risk of each delivery area; and obtain the risk prediction threshold for judging whether there is congestion behavior in each delivery area by the actual congestion situation of each delivery log in each delivery area.

[0067] The adjustment decision-making unit is used to extract abnormal features from any transport area in the transport log where the congestion risk value exceeds the risk prediction threshold, adjust the monitoring data corresponding to any abnormal feature, and generate an adjustment decision.

[0068] The prediction model building unit includes:

[0069] From the selected transport logs, arbitrarily select a transport region and obtain several abnormal features contained within that region. Calculate the feature value range for each abnormal feature, where the feature value range of the j-th abnormal feature in the transport region is set to [d]. j (min),d j [(max)]; Obtain the normal numerical range (d1) of the j-th abnormal feature. j ,d2 j Let a feature deviation value Q be assigned to the j-th anomalous feature. j If d j (max) < d1 j Then Q j =d j (max), if d2 j <d j (min), then Q j =d j (min); the deviation amplitude of the j-th abnormal feature is obtained as η. j =[Min(|Q j -d1 j |,|Q j -d2 j |)] / [Select(d1 j ,d2j ]], where Min() is the minimum value function and Select() is the selection function. If the minimum value function obtains |Q j -d1 j |, then Select(d1) j ,d2 j )=d1 j If we take the minimum value of the function, we get |Q j -d2 j |, then Select(d1) j ,d2 j )=d2 j ;

[0070] Example 1: An abnormal feature is identified in the conveying area as pressure anomaly, with a value range of (12, 15). The normal value range for the pressure feature is (5, 10). Therefore, the feature deviation value is 12, and the deviation amplitude is calculated as η = (12 - 10) / 10 = 20%.

[0071] The number of times the j-th anomaly occurs in all delivery logs is m. j The number of behaviors containing the j-th anomalous feature among all congestion behaviors is n. j The anomaly weight f of the j-th anomalous feature is calculated. j =n j / m j ;

[0072] Congestion prediction model is constructed to calculate the predicted congestion risk value R for the transport area. ex :

[0073] ;

[0074] Where b represents the number of abnormal features in the transport area; if congestion occurs in the selected transport area from the selected transport logs, then the congestion risk prediction value R is... ex Set as the abnormal prediction value; obtain the abnormal prediction value of any congestion behavior in the transportation area, and select the abnormal prediction value with the smallest value as the risk prediction threshold for judging whether there is congestion behavior in the transportation area.

[0075] Example 2: In a delivery area obtained from the delivery log, there are 3 abnormal features with deviation amplitudes and abnormal weights of (20%, 0.8), (25%, 0.7), and (20%, 0.9), respectively. The congestion risk prediction value R is calculated. ex =0.2×0.8+0.25×0.7+0.2×0.9=0.16+0.175+0.18=0.515.

[0076] The adjustment of the decision-making unit includes:

[0077] Set the risk prediction threshold as R th Select a transport region from any transport log. If the predicted congestion risk value obtained for the selected transport region is R... ex If R ex ≥R th Then, all abnormal features contained in the selected transport area are extracted;

[0078] The system identifies the monitoring equipment containing any abnormal feature, formulates an adjustment plan to adjust the conveyor belt in the selected conveying area, and ensures that the monitoring data of the monitoring equipment is within the normal range. It also formulates corresponding adjustment plans for all abnormal features and generates an adjustment decision for the selected conveying area.

[0079] The real-time prediction and feedback module is used to monitor the real-time conveying process on the conveyor belt, obtain a real-time conveying log, predict congestion based on the real-time conveying log and make timely adjustments; monitor the changes in abnormal characteristics after adjustment, identify existing abnormalities and issue reminders.

[0080] The real-time prediction and feedback module includes a real-time delivery prediction unit and an abnormal congestion feedback unit.

[0081] The real-time delivery prediction unit is used to acquire monitoring data from various monitoring devices in the real-time delivery log, obtain the monitoring data of any monitoring device at the current monitoring time point, and if the monitoring data at the current monitoring time point does not belong to the preset normal value range, then it extracts abnormal features from the monitoring devices and obtains the deviation amplitude η of the monitoring data. now The abnormal weight f of the extracted abnormal features is obtained; the abnormal weight of each abnormal feature in any transport area and the deviation of the corresponding monitoring data are obtained and input into the congestion prediction model to obtain the congestion risk prediction value of each transport area in the real-time transport log; and the transport areas whose congestion risk prediction value exceeds the risk prediction threshold are adjusted.

[0082] The abnormal congestion feedback unit is used to acquire the monitoring data of each monitoring device in the adjusted transport area at regular intervals. If the monitoring data of a monitoring device is not within the normal value range for several consecutive monitoring time points, an abnormality reminder is sent to the adjusted transport area.

[0083] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above, and that the invention can be implemented in other specific forms without departing from its spirit or essential characteristics. Therefore, the embodiments should be considered in all respects as exemplary and non-limiting, and the scope of the invention is defined by the appended claims rather than the foregoing description. Thus, all variations falling within the meaning and scope of equivalents of the claims are intended to be included within the present invention. No reference numerals in the claims should be construed as limiting the scope of the claims.

Claims

1. A flexible production conveyor belt dynamic speed regulation intelligent matching system, characterized in that: The matching system includes a transportation data analysis module, a congestion feature analysis module, a transportation prediction and decision-making module, and a real-time prediction feedback module; The conveying data analysis module is used to collect data on each conveying process of the conveyor belt through preset monitoring equipment and generate a conveying log; identify congestion behaviors in any conveying log and obtain a set of congestion behaviors for any conveying log. The congestion feature analysis module is used to compare the differences between each congestion behavior in all congestion behavior sets, classify different congestion behaviors into categories, identify abnormal features of any type of congestion behavior, and analyze the feature range of each abnormal feature. The transport prediction and decision module is used to construct a congestion prediction model to predict the congestion situation of transport logs, and to train it based on the actual congestion situation of any transport log; and to make corresponding adjustment decisions for various congestion behaviors based on the prediction results. The real-time prediction feedback module is used to monitor the real-time conveying process on the conveyor belt, obtain a real-time conveying log, predict congestion based on the real-time conveying log and make timely adjustments; monitor changes in abnormal characteristics after adjustment, identify existing abnormalities and issue reminders. The delivery prediction decision module includes a prediction model construction unit and an adjustment decision-making unit; The prediction model construction unit is used to arbitrarily select a delivery log, analyze the deviation of abnormal features contained in any delivery area in the selected delivery log, analyze the frequency of abnormal occurrence of each abnormal feature, obtain the abnormal weight of each abnormal feature, construct a congestion prediction model to predict the congestion risk of each delivery area; and obtain the risk prediction threshold for judging whether there is congestion behavior in the delivery area by the actual congestion situation of each delivery log in each delivery area. The adjustment decision-making unit is used to extract abnormal features from any transportation area in any transportation log where the congestion risk value exceeds the risk prediction threshold, adjust the monitoring data corresponding to any abnormal feature, and generate an adjustment decision. The prediction model construction unit includes: From the selected transport logs, arbitrarily select a transport region and obtain several abnormal features contained within that region. Calculate the feature value range for each abnormal feature, where the feature value range of the j-th abnormal feature in the transport region is set to [d]. j (min),d j [(max)]; Obtain the normal numerical range (d1) of the j-th abnormal feature. j ,d2 j Let a feature deviation value Q be assigned to the j-th anomalous feature. j If d j (max) < d1 j Then Q j =d j (max), if d2 j <d j (min), then Q j =d j (min); the deviation amplitude of the j-th abnormal feature is obtained as η. j =[Min(|Q j -d1 j |,|Q j -d2 j |)] / [Select(d1 j ,d2 j ]], where Min() is the minimum value function and Select() is the selection function. If the minimum value function obtains |Q j -d1 j |, then Select(d1) j ,d2 j )=d1 j If we take the minimum value of the function, we get |Q j -d2 j |, then Select(d1) j ,d2 j )=d2 j ; The number of times the j-th anomaly occurs in all delivery logs is m. j The number of behaviors containing the j-th anomalous feature among all congestion behaviors is n. j The anomaly weight f of the j-th anomalous feature is calculated. j =n j / m j ; Congestion prediction model is constructed to calculate the predicted congestion risk value R for the transport area. ex : ； Where b represents the number of abnormal features in the transport area; if congestion occurs in the selected transport area from the selected transport logs, then the congestion risk prediction value R is... ex Set as the abnormal prediction value; obtain the abnormal prediction value of any congestion behavior in the transportation area, and select the abnormal prediction value with the smallest value as the risk prediction threshold for judging whether there is congestion behavior in the transportation area. The adjustment decision-making unit includes: Set the risk prediction threshold as R th Select a transport region from any transport log. If the predicted congestion risk value obtained for the selected transport region is R... ex If R ex ≥R th Then, all abnormal features contained in the selected transport area are extracted; The system identifies the monitoring equipment containing any abnormal feature, formulates an adjustment plan to adjust the conveyor belt in the selected conveying area, and ensures that the monitoring data of the monitoring equipment is within the normal range. It also formulates corresponding adjustment plans for all abnormal features and generates an adjustment decision for the selected conveying area.

2. The intelligent matching system for dynamic speed regulation of a flexible production conveyor belt according to claim 1, characterized in that: The transport data analysis module includes a transport log collection unit and a transport congestion identification unit; The conveyor log collection unit is used to divide the conveyor belt into several conveying areas according to a preset functional type, and to install corresponding monitoring equipment in each conveying area; whenever the conveyor belt starts conveying, each monitoring device starts to collect conveying data in the corresponding conveying area until the conveyor belt stops conveying; the monitoring data collected during each complete conveying process is presented according to the monitoring time to show the data changes, and the corresponding conveying log is obtained. The transport congestion identification unit is used to arbitrarily select a transport log, arbitrarily select a monitoring device from the selected transport log, extract the monitoring data of the monitoring device at any monitoring time point, set the monitoring data detected by each monitoring device as a type of monitoring data, and preset a normal value range for each type of monitoring data. Specifically, a normal value range r=(d1,d2) is preset for the selected monitoring device, where d1 is the minimum value and d2 is the maximum value. The value of the monitoring data at monitoring time point t0 is set as d. t0 ,like Then, obtain several monitoring time points that are adjacent to and consecutive to the monitoring time point t0. If the values ​​of the monitoring data under the several monitoring time points are not within the normal value range, then merge the several monitoring time points to obtain a time interval, and obtain the transmission behavior in the time interval to obtain a congestion behavior of the transmission log; obtain the congestion behavior of each time interval to obtain the set of congestion behaviors of the selected transmission log.

3. The intelligent matching system for dynamic speed regulation of a flexible production conveyor belt according to claim 2, characterized in that: The congestion feature analysis module includes a transportation congestion segmentation unit and an abnormal feature identification unit; The delivery congestion classification unit is used to select any congestion behavior from a certain delivery log, acquire the time interval and various monitoring data of the selected congestion behavior; compare the differences between the time interval and monitoring data of any two congestion behaviors, and determine whether to classify the two user behaviors. The abnormal feature identification unit is used to analyze the abnormal situations of any congestion behavior in various types of monitoring data within any category of the same type, and extract several abnormal features. Furthermore, the monitoring data corresponding to any abnormal feature in different congestion behaviors are extracted to obtain the feature value range of any abnormal feature.

4. The intelligent matching system for dynamic speed regulation of a flexible production conveyor belt according to claim 3, characterized in that: The transport congestion division unit includes: Arbitrarily select a delivery log, and arbitrarily select a congestion behavior from that delivery log. Set the selected congestion behavior as the target congestion behavior, and obtain the time interval of the target congestion behavior as (t). g1 ,t g2 ); Obtain the conveying speed of the conveyor belt in each conveying zone, and obtain the expected time interval for each conveying zone. The expected time interval for the i-th conveying zone is set as (t1...). i ,t2 i If (t) g1 ,t g2 )∈(t1 i ,t2 i If the expected occurrence area of ​​the target congestion behavior is obtained as the i-th transport area, and the actual occurrence area of ​​the target congestion behavior is captured by the monitoring equipment as the a-th transport area, a transport deviation flag F is set. If i ≠ a, then a first deviation flag F is set. (i,a) Make F=F (i,a) If i=a, then set the second deviation flag F. i Make F=F i ; The monitoring data of any selected monitoring device changes over time. The normal value range of the selected monitoring device is obtained. If the monitoring value at any monitoring time point in a continuous time interval does not belong to the normal value range, the selected monitoring device is marked as abnormal, and the set A of monitoring devices with abnormal markings in the target congestion behavior is obtained. Select another congestion behavior from the remaining congestion behaviors and set it as the comparison congestion behavior, then obtain the transport deviation flag F of the comparison congestion behavior. ’ and the collection A of all monitoring devices containing anomaly markers ’ If F ’ =F and A=A ’ If the target congestion behavior and the comparison congestion behavior are classified as similar congestion behaviors, then they are classified as different congestion behaviors.

5. The intelligent matching system for dynamic speed regulation of a flexible production conveyor belt according to claim 4, characterized in that: The abnormal feature identification unit includes: Select any group of similar congestion behaviors and extract the set of monitoring devices with anomaly markers within that group. From this set, randomly select one monitoring device and obtain its monitoring data from all transport logs, thus obtaining a complete numerical range (d). min ,d max The normal value range of the monitoring equipment is set to (d1, d2). If d1 > d2, then... min Then we get a deviation range p1=(d min ,d1), if d2 < d max Then we get a deviation range p2=(d2,d max ); If the selected monitoring equipment has a deviation range, the data type of the monitoring data is set to the abnormal features of the selected monitoring equipment; the abnormal features of each monitoring equipment in each transmission log containing the same type of congestion behavior are extracted to obtain several abnormal features of the same type of congestion behavior. By arbitrarily selecting an anomaly feature, and acquiring the transport logs of any congestion behavior within the same type of congestion behavior, the range of deviation values ​​(d1) of the monitoring equipment containing the selected anomaly feature is obtained. ’ ,d2 ’ If d1 ’ <d2<d2 ’ Then the actual deviation range of the corresponding delivery log is (d2, d2) ’ Extract the actual deviation range of each congestion behavior in the same type of congestion behavior and take the intersection to obtain the feature value range of the selected abnormal features.

6. The intelligent matching system for dynamic speed regulation of a flexible production conveyor belt according to claim 5, characterized in that: The real-time prediction feedback module includes a real-time transmission prediction unit and an abnormal congestion feedback unit. The real-time delivery prediction unit is used to acquire monitoring data from each monitoring device in the real-time delivery log, obtain the monitoring data of any monitoring device at the current monitoring time point, and if the monitoring data at the current monitoring time point does not belong to the preset normal value range, then extract abnormal features from the monitoring device and obtain the deviation amplitude η of the monitoring data. now The abnormal weight f of the extracted abnormal features is obtained; the abnormal weight of each abnormal feature in any transport area and the deviation of the corresponding monitoring data are obtained and input into the congestion prediction model to obtain the congestion risk prediction value of each transport area in the real-time transport log; and the transport areas whose congestion risk prediction value exceeds the risk prediction threshold are adjusted. The abnormal congestion feedback unit is used to acquire the monitoring data of each monitoring device in the adjusted transport area at regular intervals. If the monitoring data of a monitoring device is not within the normal value range for several consecutive monitoring time points, an abnormality reminder is sent to the adjusted transport area.

Images