Conveying belt intelligent control system based on coal selecting and washing

Abstract

The invention relates to the technical field of data processing, in particular to an intelligent conveyor belt control system based on coal selecting and washing, which comprises a data acquisition module, a state segmentation module, an operation monitoring module, a load association module and a fault processing module, the method comprises the following steps: collecting an operation feature vector and a coal feature vector of the operation of a conveying belt, dividing the conveying belt into a plurality of feature units, and setting a plurality of state recognition areas according to feature threshold values of the coal feature vector and the operation feature vector under each feature unit; performing data monitoring on the plurality of state identification areas, generating a plurality of characteristic curves, and identifying a correlation model of the coal characteristic vector and the operation characteristic vector; verifying a fault type of each association event under the association degree, determining a risk weight corresponding to the fault type, and checking the processing schemes existing in the database to obtain a fault processing scheme; the efficiency and the stability during coal conveying are achieved, and the risk and the cost in the production process are reduced.

Description

Technical Field

[0001] The invention relates to the technical field of data processing, and in particular to an intelligent control system for a conveyor belt based on coal selection and washing. Background Art

[0002] In the process of coal washing, the conveyor belt is one of the key equipment, and its operating status directly affects the efficiency and product quality of the entire production line. However, the traditional coal washing process often relies on manual monitoring and manual adjustment, which has problems such as low efficiency and easy errors. At the same time, due to the complexity and uncertainty of the coal washing process, fault warning and diagnosis also face great challenges. Therefore, it is of great significance to develop a coal washing conveyor belt control system based on intelligent technology.

[0003] For example, Chinese patent publication number CN115196275A discloses a speed regulation method, device, equipment, storage medium and multi-layer conveyor line thereof, comprising: obtaining the operating status of each unit; determining a target conveyor belt when it is detected that the operating status of at least one processing mechanism in each unit is abnormal; adjusting the initial speed of the target conveyor belt to a first speed according to a first instruction; the first instruction is generated after determining the target conveyor belt; the unit is composed of at least two identical processing mechanisms; the target conveyor belt is a conveyor belt corresponding to a processing mechanism with a normal operating status in the unit where the processing mechanism with an abnormal operating status is located; the first speed is less than the initial speed.

[0004] For example, Chinese patent publication number CN115611029A discloses an intelligent coal loading method and system, which obtains the filling feature vector and discharge port state vector of a carriage during the process of coal loading a carriage by a coal filling system; divides a set number of carriages into a preset number of categories; obtains the minimum height threshold, height peak threshold and discharge port state vector threshold under each category; obtains the random factor of the filling feature vector of each carriage; divides the filling feature vector of the carriage into normal samples and abnormal samples using the random factor; trains a binary classification model using the normal samples and the abnormal samples; and uses the trained binary classification model, the minimum height threshold, the height peak threshold and the discharge port state vector threshold under each category to control the operating parameters of the coal filling system for coal loading.

[0005] The prior art describes that the speed can be adjusted by the operating status of multiple machines, and the height of the coal identified at multiple times can be used to adjust the working process of coal transportation; however, under this processing method, it is difficult to find the relationship between the equipment-related vector and the coal-related vector during coal transportation, and whether the relationship is related to the abnormal situation of the conveyor belt. Therefore, it is necessary to monitor and process the data related to the conveyor belt as a whole to improve the safety of coal transportation and processing. Summary of the invention

[0006] In order to solve the above technical problems, the technical solution adopted by the present invention is: an intelligent control system for a conveyor belt based on coal washing, including: a data acquisition module, used to collect status information, coal flow and conveyor belt speed during the operation of the conveyor belt, as the operation characteristic vector of the conveyor belt operation; coal moisture and coal particle size distribution are used as coal-related coal characteristic vectors.

[0007] The state segmentation module is used to divide the conveyor belt into multiple feature units according to the coal feature vectors and operation feature vectors at different positions during coal selection and washing, and to set multiple state recognition areas according to the feature thresholds of the coal feature vectors and operation feature vectors under each feature unit.

[0008] The operation monitoring module is used to monitor data of multiple state identification areas, generate multiple characteristic curves according to coal characteristic vectors and operation characteristic vectors, analyze the characteristic curves, and identify the association model between the coal characteristic vectors and the operation characteristic vectors.

[0009] The associated load module is used to determine the degree of association during coal washing according to the association model of the coal characteristic vector and the operation characteristic vector; verify the fault type of each associated event under the corresponding degree of association, and output the basic event combination corresponding to the fault type.

[0010] The fault handling module is used to determine the risk weight corresponding to the fault type according to the acquired fault type, and check the handling solutions existing in the database to obtain the fault handling solution corresponding to the current fault type.

[0011] The beneficial effects of the present invention are as follows: First, the present invention uses the state information of coal operation, coal flow and conveyor belt speed as the operation characteristic vectors of the conveyor belt operation, so as to understand the working conditions of each conveyor belt between the corresponding working settings when the conveyor belt transports the corresponding coal, and can timely reflect the corresponding conveyor belt problems during coal transportation, so as to facilitate subsequent timely targeted processing; at the same time, the present invention uses the coal humidity and coal particle size distribution as the coal characteristic vectors related to coal, so as to understand the specific conditions of the coal in the selection and washing process and prevent the problem of blockage in coal transportation.

[0012] 2. The present invention divides the conveyor belt into multiple state identification areas by using coal feature vectors and operation feature vectors, and performs correlation analysis on the data in the state identification areas. This can improve the correlation between work-related information and the coal itself during data processing, and obtain a model data that can accurately feedback the correlation, thereby ensuring the stability and consistency of product quality during coal production.

[0013] 3. The present invention uses corresponding events in the association model and uses a fault tree to analyze the corresponding associated events, so as to obtain the types of faults that are prone to occur under the current multiple data associations, and describes the fault types using risk weights and specific values, which can further identify faults that occur in the production process and control the risks and costs in the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The present invention is further described below in conjunction with the accompanying drawings and embodiments.

[0015] Figure 1 It is a system framework diagram of a conveyor belt intelligent control system based on coal selection and washing.

[0016] Figure 2 The present invention is a flow chart of a state segmentation module of a conveyor belt intelligent control system based on coal selection and washing.

[0017] Figure 3 The present invention is a flow chart of an operation monitoring module of a conveyor belt intelligent control system based on coal selection and washing. DETAILED DESCRIPTION

[0018] The embodiments of the present invention are described in detail below. The embodiments described below are exemplary and are only used to explain the present invention, and should not be construed as limiting the present invention. If no specific techniques or conditions are specified in the embodiments, the techniques or conditions described in the literature in the art or the product specifications are used.

[0019] See also Figure 1 A conveyor belt intelligent control system based on coal selection and washing includes: a data acquisition module, a state segmentation module, an operation monitoring module, an associated load module and a fault processing module; wherein the output end of the data acquisition module is connected to the state segmentation module, the output end of the state segmentation module is connected to the operation monitoring module, the output end of the operation monitoring module is connected to the associated load module, and the output end of the associated load module is connected to the fault processing module.

[0020] The data acquisition module is used to collect the state information, coal flow rate and conveyor belt speed of the conveyor belt during operation as the operation characteristic vector of the conveyor belt; and the coal moisture and coal particle size distribution are used as the coal characteristic vector related to the coal.

[0021] The state segmentation module is used to divide the conveyor belt into multiple feature units according to the coal feature vectors and operation feature vectors at different positions during coal selection and washing, and to set multiple state recognition areas according to the feature thresholds of the coal feature vectors and operation feature vectors under each feature unit.

[0022] The operation monitoring module is used to monitor data of multiple state identification areas, generate multiple characteristic curves according to coal characteristic vectors and operation characteristic vectors, analyze the characteristic curves, and identify the association model between the coal characteristic vectors and the operation characteristic vectors.

[0023] The associated load module is used to determine the degree of association during coal washing according to the association model of the coal characteristic vector and the operation characteristic vector; verify the fault type of each associated event under the corresponding degree of association, and output the basic event combination corresponding to the fault type.

[0024] The fault handling module is used to determine the risk weight corresponding to the fault type according to the acquired fault type, and check the handling solutions existing in the database to obtain the fault handling solution corresponding to the current fault type.

[0025] The above status information includes the temperature of the conveyor belt, the operating mark of whether the conveyor belt is operating normally, and the mark of whether the conveyor belt is blocked during operation, to determine whether the current conveyor belt can transport coal normally when the conveyor belt is connected to the coal washing equipment.

[0026] Conveyor belt temperature: Temperature sensors can be installed to obtain conveyor belt temperature data. These sensors can monitor the temperature changes of the conveyor belt in real time to ensure that the equipment operates within a safe temperature range.

[0027] Operation flag: The combination of controller and sensor can be used to determine whether the conveyor belt is in normal operation. For example, by monitoring the motor current, vibration and other parameters of the conveyor belt, it can be determined whether there is an abnormality. The operation flag obtained here is mainly used to determine whether the current conveyor belt is operating normally and the corresponding status of startup and shutdown.

[0028] Blockage sign: Installing a pressure sensor or weight sensor on the conveyor belt can monitor the weight change of the coal on the conveyor belt in real time to determine whether there is a blockage. When the weight exceeds the set threshold, the system can issue an alarm. At the same time, this sign is set by identifying whether there is too much coal and overall blockage.

[0029] Coal flow: Use flowmeter or weighing sensor to measure the coal flow through the conveyor. By monitoring the speed and time of coal flow, the amount of coal can be calculated to obtain coal flow data. This unit will indicate the corresponding weight of coal allowed to flow in a fixed time.

[0030] Conveyor belt speed: High-precision speed measurement equipment such as laser speed meters and radar speed meters can be used to measure the speed of the conveyor belt in real time. These devices usually have the characteristics of fast response and high precision, which can ensure the accuracy of the measurement results.

[0031] Coal moisture: The measurement of coal moisture can be achieved through humidity sensors. These sensors can monitor the humidity changes of coal in real time, which is of great significance for ensuring the quality of coal storage and transportation.

[0032] Coal particle size distribution: The particle size distribution of coal is measured by mechanical screening, microscopic observation, image processing or laser particle size analysis. These methods can conduct qualitative and quantitative analysis of coal based on the particle size, shape and distribution of coal.

[0033] Sieving method: The coal sample is sieved through a series of sieves with different apertures to separate the coal particles into fractions of different particle sizes. The coal sample is placed in the top sieve and the sieve is vibrated or shaken to allow the particles to pass through the sieve holes in order of size. The residual particles on each sieve are collected and weighed. Based on the mass of the residual particles on each sieve, the mass percentage of each fraction is calculated to obtain the particle size distribution.

[0034] Laser particle size analysis method: Using the principle of laser scattering, the particle size distribution is calculated by measuring the scattered light intensity of coal particles in the laser beam. The coal sample is placed in the laser particle size analyzer, and the instrument will emit a laser beam and measure the scattered light intensity. According to the distribution of the scattered light intensity, the particle size distribution is calculated. According to these two methods, the particle size of the coal itself can be known, and combined with the humidity of the coal, the current state and condition of the coal can be more comprehensively understood.

[0035] The acquisition of these parameters can monitor the operating status of the conveyor belt and the coal flow in real time, and can promptly discover and solve potential production problems, such as conveyor belt blockage, insufficient coal supply, etc., thereby ensuring the stable operation of the production line and improving production efficiency.

[0036] The implementation method of the operation characteristic vector also includes: according to the state information at each sampling moment, the obtained coal flow and conveyor belt speed are associated, and the first difference between the coal flow and the preset coal flow and the second difference between the conveyor belt speed and the preset conveyor belt speed are calculated respectively, and after converting the first difference and the second difference into a ratio, the product corresponding to the first difference and the second difference is obtained as the associated value of the coal flow and the conveyor belt speed. The preset coal flow and the preset conveyor belt speed represent the average coal flow and the average conveyor belt speed of the current coal selection and washing production line when the coal is normally produced. At this time, the first difference and the second difference are obtained to determine whether the current conveyor belt is inconsistent with normal production when transporting coal for selection and washing, and this inconsistent situation is combined with the value of the state information under different circumstances to obtain a value representing the production state. The first difference and the second difference are converted into a ratio by comparing the first difference and the second difference with the preset coal flow and the preset conveyor belt speed.

[0037] The average value of the correlation value of coal flow and conveyor belt speed under the same state information is calculated, and the average value is used as the eigenvalue of the operation feature vector; this eigenvalue can be used as part of the operation feature vector for subsequent monitoring, analysis or decision support. For example, it can be used to identify potential problems in the production process, optimize production parameters or predict equipment failures.

[0038] The same status information represents the average of the differences generated under the same conveyor belt temperature, the same operating sign, and the same blocking situation sign. The operating sign is generally represented by normal operation, shutdown, standby, deceleration operation, etc., which describe the operating conditions. The temperature records the temperature of the conveyor belt when it is receiving coal for processing. The blocking situation sign is a sign of whether there is a blockage or not.

[0039] The implementation method of the coal characteristic vector also includes: obtaining the maximum coal moisture, the maximum coal particle size distribution, the average coal moisture and the average coal particle size distribution according to the coal moisture and the coal particle size distribution at each sampling moment, and calculating the moisture similarity index between the maximum coal moisture and the average coal moisture and the particle size similarity index between the maximum coal particle size distribution and the average coal particle size distribution respectively; and taking the weighted sum of the moisture similarity index and the particle size similarity index as the correlation value of the coal moisture and the coal particle size distribution.

[0040] The average value of the correlation value between coal moisture and coal particle size distribution under the same state information is calculated, and the average value is used as the eigenvalue of the coal eigenvector.

[0041] Here, the data at the sampling time is analyzed to determine the stability and consistency of the coal feature vector under the corresponding time changes. The moisture similarity index and the particle size similarity index can be calculated by the cosine similarity method or the Pearson correlation coefficient and other calculation methods to obtain the index. Then, the weighted sum of the two is taken to obtain a relative feature value. At the same time, this weighted sum is used as part of the coal feature vector to improve the accuracy of subsequent classification processing of the coal feature vector.

[0042] In one embodiment of the present invention, the state segmentation module is mainly divided according to the characteristic values ​​corresponding to the coal characteristic vector and the operation characteristic vector, and the characteristic threshold is the value taken to divide the characteristic value into multiple intervals to indicate what areas the coal characteristic vector and the operation characteristic vector should be divided into under different values, and whether corresponding problems will occur when the conveyor belt transports coal in these areas.

[0043] like Figure 2As shown, the implementation method of the state segmentation module includes: according to the position of the conveyor belt, the coal feature vectors and the operation feature vectors in the feeding area, the processing area and the discharging area are determined in turn, and the conveyor belt is divided into multiple feature units; here, the conveyor belt is distributed according to the position, and the corresponding vector is matched with the position of the conveyor belt to determine the changes of the characteristics corresponding to the coal on different conveyor belts during the coal selection and washing process, and the data identified at these positions are linked with the data of the normal operation of the production line to find out whether there are any abnormal conditions in the current production process.

[0044] Feeding area: Here the main focus is on the initial characteristics of the coal, such as moisture, particle size distribution, etc.

[0045] Processing area: includes the conveying section between various processing equipment, which requires monitoring of changes in coal characteristics and equipment operating status.

[0046] Discharging area: focuses on the quality characteristics of the final product.

[0047] Identify the main component vectors of the coal feature vector and the operation feature vector on each feature unit, and select the feature thresholds of the coal feature vector and the operation feature vector according to the value of the main component vector. At this time, the feature thresholds of the coal feature vector and the operation feature vector will select the selection content of the main component vector on different feature units, indicating the value required for the feature unit to divide the state recognition area.

[0048] The principal component vectors describe the features that are primarily identified at the relative locations of the conveyor belt on the feed zone, the processing zone, and the discharge zone, for example, the feed zone primarily identifies coal flow, coal moisture, and coal particle size distribution.

[0049] The processing area mainly identifies the conveyor belt speed, coal load and foreign matter detection. The coal load is obtained by identifying the coal flow entering the conveyor belt per unit time. The foreign matter detection is obtained through the blockage mark in the status information to determine whether there is a large blockage and whether the conveyor belt is overloaded.

[0050] The discharge area mainly identifies coal moisture, coal particle size distribution, and blockage signs in status information to determine whether the coal quality will be affected by external conditions.

[0051] These contents are the main component vectors on each feature unit. Then, according to the contents that need to be identified by these main component vectors, the feature threshold for judgment is selected. For the iconic information, its value is 0, 1, 2, 3 or marked in the form of 0, 1, 0 means there is no problem, 1, 2, 3 represent the corresponding degree of problem, or 1 represents the problem sign, to describe whether there is a problem in the corresponding area of ​​the current conveyor belt; other numerical features use the boundary values ​​identified in the historical data, or use the average value or minimum and maximum values ​​of the corresponding features under warning, abnormal and normal operation conditions to set the feature threshold at this time.

[0052] For example, the display of the feeding area in normal, warning and abnormal states is shown as follows.

[0053] Normal state: Set a reasonable coal flow range (for example, 100 to 200 tons per hour), control the coal humidity within a range that does not affect fluidity (such as less than 8%), and the coal particle size distribution meets the preset standards (for example, the proportion of particles <5mm does not exceed 30%).

[0054] Warning status: If the coal flow rate is close to the upper or lower limit (such as 90 or 210 tons / hour), the humidity is slightly higher than the recommended value (such as 8%-10%), or the coal particle size distribution deviates slightly, an early warning will be triggered to prompt the operator to pay attention.

[0055] Abnormal state: When the coal flow exceeds the safety range (lower than 80 or higher than 220 tons / hour), the humidity is too high (more than 10%) or the coal particle size distribution deviates seriously from the standard, the system should immediately alarm and take measures (such as slowing down the conveyor belt speed or stopping feeding).

[0056] For example, the processing area is represented in normal, warning and abnormal states as shown below.

[0057] Normal state: The appropriate conveyor belt speed is set (e.g. 2 m / s), the coal load is kept within the equipment design capacity (e.g. not exceeding 80% of the maximum load), and no foreign matter is detected.

[0058] Early warning status: A warning signal is issued when the conveyor belt speed slightly deviates from the set value (±0.2 m / s), the coal load approaches the upper limit (75%-80%), or small-sized foreign objects are occasionally detected.

[0059] Abnormal conditions: If the conveyor belt speed deviates significantly from the set value (more than ±0.5 m / s), the coal load exceeds the standard, or large pieces of foreign matter are frequently detected, immediate action is required to prevent damage to the equipment or blockage.

[0060] For example, the display of the discharge area in normal, warning and abnormal conditions is shown below.

[0061] Normal state: Ensure that the coal quality at discharge meets the requirements (such as specific moisture level and ideal particle size distribution), the conveyor belt runs smoothly without obstruction, and the environmental conditions are suitable.

[0062] Warning status: If the discharge quality is found to be slightly reduced (such as humidity increases to 9%, particle size distribution slightly deviates from the ideal value), or if slight signs of poor transmission are observed, timely attention should be paid.

[0063] Abnormal state: Once the discharge quality obviously does not meet the standards (such as humidity exceeding 10%, particle size distribution seriously deviates), or serious transmission blockage occurs, the machine must be stopped immediately to check and correct the problem.

[0064] According to the thresholds described for the corresponding main component vectors at different positions, the areas divided by the feature thresholds will be defined as normal working areas, warning areas and fault areas. The data under abnormal conditions will be considered as fault areas with fault risks, so as to facilitate the subsequent timely review of the fault problems of the current conveyor belt during coal washing.

[0065] The characteristic thresholds of the coal characteristic vector and the operation characteristic vector are used to define the characteristic units, which are defined as the normal working area, the warning area and the fault area in turn; the defined characteristic units are used as the output state recognition area. The final state recognition area will represent the relative working conditions of the conveyor belt at different positions to assist in the subsequent verification of whether the coal on different conveyor belts is transported normally.

[0066] At the same time, when dividing the state identification area, it can also be divided according to the characteristic values ​​calculated by the coal characteristic vector and the operation characteristic vector. The characteristic values ​​referred to in this part are the characteristic values ​​calculated by the data acquisition module for the correlation between coal flow and conveyor belt speed, and the correlation between coal humidity and coal particle size distribution. If this characteristic value is used as the subsequent characteristic threshold, the current scenario of the conveyor belt will become a scenario in which the correlation between coal flow, conveyor belt speed, coal humidity and coal particle size distribution is used as the main identification parameter. That is, it is divided into multiple state identification areas according to the correlation between the corresponding data of the coal characteristic vector and the operation characteristic vector. The state identification areas here will include normal transportation state area, flow overload state area, insufficient flow state area, humidity abnormal state area, particle size distribution abnormal state area and comprehensive fault state area; these areas will represent the state identification area in the normal working area, warning area and fault area according to the values ​​in the main component vector, further explaining the type corresponding to the state identification area, so as to facilitate the subsequent generation of characteristic curves for corresponding problems.

[0067] Normal conveying state area: In this area, the coal flow, conveyor belt speed, coal moisture and particle size distribution are all within the preset normal range; the conveyor belt runs stably, and the coal is transported continuously and evenly without additional control or adjustment.

[0068] Flow overload state area: The coal flow exceeds the preset maximum value, which may cause conveyor belt overload. It is necessary to increase the conveyor belt speed, start the backup conveyor belt, or adjust the upstream coal feed to reduce the load. There may be risks such as coal accumulation and conveyor belt slippage.

[0069] Insufficient flow state area: The coal flow is lower than the preset minimum value, and the conveyor belt operating efficiency is reduced. The conveyor belt speed can be reduced to save energy, or the upstream coal feeding equipment can be checked for faults. Long-term insufficient flow may cause the conveyor belt to run without load, increasing energy consumption and wear.

[0070] Abnormal humidity area: The coal humidity is too high or too low, exceeding the preset range. Too high humidity may cause conveyor belt slippage, coal sticking and other problems; too low humidity may cause coal dust to fly and conveyor belt wear to increase, and drying or humidification measures need to be taken to adjust the coal humidity.

[0071] Abnormal particle size distribution area: The coal particle size distribution does not meet the preset requirements. The particle size is too large or too small. Too large particle size may cause conveyor belt blockage; too small particle size may increase conveyor belt wear and energy consumption. Screening or crushing measures are required to adjust the coal particle size distribution.

[0072] Comprehensive fault status area: When multiple parameters deviate from the normal range at the same time, it may enter the comprehensive fault status area. At this time, it is necessary to comprehensively consider the impact of various parameters and take comprehensive measures to troubleshoot and deal with the faults, which may involve shutting down the conveyor belt for maintenance, replacing damaged parts, etc.

[0073] When the defined characteristic unit is used as the output state identification area, it also includes: extracting the characteristic value corresponding to the correlation value of coal flow and conveyor belt speed on the defined characteristic unit as the first boundary condition; the characteristic value described here is the average value calculated by the correlation value of coal flow and conveyor belt speed under the same state information, and this average value represents the correlation between coal flow and conveyor belt speed in a characteristic unit area.

[0074] The characteristic value corresponding to the correlation value of the coal moisture and the coal particle size distribution on the defined characteristic unit is extracted as the second boundary condition; the characteristic value described here is the average value calculated under the same state information of the coal moisture and the coal particle size distribution.

[0075] According to the first boundary condition and the second boundary condition, the state identification area is processed to determine the distribution position of each state identification area. At this time, the first boundary condition and the second boundary condition are used to further divide the current state identification area to obtain the areas with different correlations between coal moisture and coal particle size distribution, as well as coal flow and conveyor belt speed under each characteristic unit, so as to perform more detailed feature identification on the currently set state identification unit, so as to facilitate the subsequent comprehensive review of these data.

[0076] For example, after a feature unit is defined, there will be areas of insufficient flow, abnormal humidity, abnormal particle size distribution, etc. In this case, the data on the correlation between coal flow and conveyor belt speed, and coal humidity and coal particle size distribution will be further described, and data descriptions will be supplemented for these marked area locations to improve the accuracy of the overall data when setting the correlation model.

[0077] In one embodiment of the present invention, the operation monitoring module monitors the data of the normal working area, the warning area and the fault area in the state identification area, and converts the coal feature vector and the operation feature vector into a feature curve. The feature curve is generated according to the main identified features in each area. For example, according to the coal flow, coal humidity, coal particle size distribution, coal load and conveyor belt speed, multiple feature curves of different forms are generated, wherein the coal flow, coal humidity, coal load and conveyor belt speed can directly display the change of relevant data over time, and the coal particle size distribution considers the particle size of coal after crushing and other treatments. At this time, the proportion of coal particle size distribution at the corresponding time point is used to generate the feature curve corresponding to the coal particle size distribution. Then, the correlation of these different forms of feature curves is verified according to their change trends, and it is found that when the data on one feature curve is abnormal, the form of change of other feature curves will appear at the same time, or the abnormality will be distributed in a certain interval time, and then the frequent item sets of these feature curves when the abnormality occurs are found to identify the association mode of the conveyor belt when the abnormality occurs, and serve as the association model for subsequent output. At the same time, when generating these characteristic curves, other data in the coal characteristic vector and the operation characteristic vector will also be marked to identify the performance of other less important data such as the corresponding flag information in the state identification area.

[0078] like Figure 3 As shown, the implementation method of the operation monitoring module includes: standardizing the coal feature vector and the operation feature vector on the state identification area according to the type of the state identification area, obtaining at least one standard sample information, and generating multiple characteristic curves according to the values ​​of each standard sample information.

[0079] At this time, the type of the status identification area indicates the location of the current status identification area, that is, where it is located in the feeding area, processing area and discharging area, and the data at this position is set with which label in the normal working area, warning area and fault area. This label indicates the type of the status identification area.

[0080] At this time, standardization processing is performed to remove duplicate and invalid values ​​of the corresponding data in the coal characteristic vector and the operation characteristic vector, and then a dimensionless value is set on the vector to facilitate the subsequent comprehensive calculation of the relationship between multiple characteristic curves. The standard sample information obtained then represents the content after standard processing, and finally multiple characteristic curves are generated.

[0081] A relationship list is constructed for each characteristic curve. The relationship list is a list that combines the data in each characteristic curve in pairs and calculates its support. The relationship list is used to extract candidate frequent item sets; candidate frequent item sets are combinations of items with support higher than a certain threshold extracted from the transaction database or event log; support refers to the frequency with which a specific item set appears in the entire data set. For example, in the coal processing process, if high humidity and small particle size particles are observed to often appear at the same time, the item set composed of these two features is a candidate frequent item set. The support set at this time will be set according to the support of these data in normal historical data. When the support exceeds this support, it means that there may be related problems with the currently associated data.

[0082] The candidate frequent item sets are matched with the preset association rules to obtain the matching results of the candidate frequent item sets and the preset association rules, and the matching polynomials corresponding to the matching results are generated, and the association model is set according to the matching polynomials. The preset association rules refer to the rules that are pre-defined and based on domain knowledge or experience, which are used to identify patterns in the data. For example, in the coal conveyor belt system, the following association rule may be preset: "If the moisture content of the coal exceeds 8%, and the proportion of particles smaller than 5 mm in the particle size distribution exceeds 30%, blockage may occur"; here, "the moisture content of the coal exceeds 8%" and "the proportion of particles smaller than 5 mm exceeds 30%" are the conditions (the antecedents), and "blockage may occur" is the result (the consequent); then when such data is matched with the candidate frequent item sets, if the candidate frequent item sets meet all the conditions of the preset association rules, it is considered that the frequent item sets are successfully matched with this rule. For example, suppose a frequent item set is found from the data: "the moisture content of the coal is 9%, and the proportion of particles smaller than 5 mm is 32%", which just meets the above preset association rules, so this item set is successfully matched with the rule.

[0083] At the same time, the matching polynomial is used to quantify the importance or influence of the matching results. It can be quantified according to the product of the proportion of the corresponding elements in the matching results exceeding the preset data in the preset association rules, indicating the relative importance after the matching, and using the data corresponding to the matching polynomial to set the association model to predict the operation of coal during transmission.

[0084] When obtaining the matching result of the candidate frequent item set and the preset association rule, it also includes: when the candidate frequent item set meets all the conditions of the preset association rule, it is considered that the frequent item set matches the preset association rule successfully, and it is judged whether there is a successfully matched adjacent candidate frequent item set in the corresponding state identification area of ​​the current candidate frequent item set. The adjacent candidate frequent item set indicates that there is a value that successfully matches the current one in the item set. For example, the successfully matched candidate frequent item set is coal moisture and coal particle size distribution, then the adjacent candidate frequent item set contains one of the two, and if the adjacent candidate frequent item set is also successfully matched by the preset association rule, it is possible to find the corresponding data association that exists when anomalies occur, and output this part of data together. If it exists, the adjacent candidate frequent item set corresponding to the current candidate frequent item set is merged and output as the matching result of the candidate frequent item set and the preset association rule.

[0085] When generating a matching polynomial corresponding to the matching result, the data represented by all the matching results on the corresponding state recognition area can also be set as a concept graph, the successfully matched data can be expressed using a node relationship, and the output matching polynomial can be set according to the connection relationship between the corresponding data on the state area on the graph; or a comprehensive output can be performed based on the corresponding data that has been successfully matched on each feature curve to obtain the current expressed relationship model.

[0086] Therefore, the implementation method of generating the matching polynomial corresponding to the matching result includes: based on the preset association rules in the matching result, the matching result is converted into a matching node, and each matching node represents a specific concept or entity described in the preset association rule, such as "high humidity environment", "fine particle material", etc., which directly describes the content of the corresponding data on the matching node. The edge between each matching node represents the confidence between the matching nodes, which is used to describe the strength of the relationship between two matching nodes.

[0087] Connect each matching node and output the shortest path of each matching node after connection. Here, convert the confidence on each matching node into a negative number, and use the Dijkstra algorithm to find the shortest path of each matching node after connection. This path represents the path with the highest confidence. At the same time, after all matching nodes are connected and all meet the shortest path, the corresponding connection content will be output. The output content will be used as the content calculated by the subsequent matching polynomial. The proportional product or weighted sum of these values ​​exceeding the preset association rules is used as the value of the matching polynomial, and then the association model under the current analysis is formed.

[0088] If the matching is successful and the coal feature vector is combined into a matching polynomial, , the running feature vector is , m represents the number of elements in the coal feature vector, and n represents the number of elements in the operation feature vector; these data are mapped from the data that have completed the matching process to determine the association model between the coal feature vector and the operation feature vector at this time; the output of the association model is , Z represents the number of state identification areas. At this time, the data in the characteristic curve is processed according to the state identification area in which it is located, and the association between the current coal characteristic vector and the operation characteristic vector is judged according to the data output by each state identification area, and the possible faults under this association are found out.

[0089] At this time, the association model is expressed as ;in, represents the output value of the association model, represents the regression coefficient matrix, represents the error term, represents the polynomial basis function, , the polynomial basis function includes the constant term 1, the value of a single coal feature vector and a single operating feature vector, the square value of a single coal feature vector and a single operating feature vector, the interaction between two elements in the coal feature vector and the operating feature vector, and the interaction between the coal feature vector and its own elements in the operating feature vector. During regression, the output results of the association model are constantly adjusted, and the data in the calculated polynomial basis function is changed at the same time, so that when the association model outputs the data, its own error term can be minimized.

[0090] The regression coefficient matrix is ​​expressed as: ,in, represents the transposed matrix of the polynomial basis functions, Represents the regularization coefficient, which is used to prevent overfitting; Represents the identity matrix, where all elements on the main diagonal are 1, and all elements in other positions are 0. Then, when the error term is minimized, the final output value of the current association model is obtained.

[0091] In one embodiment of the present invention, the associated load model is mainly processed according to the value output by the associated model, and the associated events in the preset association rules corresponding to the value are extracted. The associated events represent events that may occur after the preset association rules are met. For example, if the moisture content of the coal exceeds 8% and the proportion of particles less than 5 mm in the particle size distribution exceeds 30%, blockage may occur. The data described above are the conditions of the preset association rules. The possibility of blockage indicates the associated events that may occur at this time. At this time, each associated event is fitted, and the most likely faults of these associated events after fitting are found. After the type is output using a fault tree, the processing set of related data under the association degree is completed.

[0092] The implementation method of the associated load module includes: extracting the association strength output by the association model of the coal feature vector and the operation feature vector, and obtaining each associated event corresponding to the degree of association. When outputting the degree of association, because the number of data contained in each matching polynomial is different, when calculating its degree of association, multiple associated events will be included, and the degree of association will output multiple values ​​at a macro level; at this time, the specific fault type that occurred is taken as the top-level event, and each associated event is taken as the basic event, and the basic events are connected to form logic gates to complete the establishment of the fault tree, and finally the associated event that the current basic event can correspond to is found.

[0093] The association event described here refers to the corresponding contents that are dynamically merged or not merged after matching the candidate frequent item sets and the preset association rules when the running monitoring module generates the association model.

[0094] If the frequent item set represents: high humidity and fine particles appear at the same time (support > 0.7); conveyor belt speed fluctuation and coal flow drop occur at the same time.

[0095] The preset association rules indicate: Rule 1: IF humidity > 8% AND fine particle ratio > 30% → predict blockage (confidence = 0.9); Rule 2: IF temperature > 60°C AND speed fluctuation > 10% → predict motor overheating (confidence = 0.85).

[0096] If the associated events of adjacent status areas are triggered at the same time (such as abnormal humidity in the feeding area + abnormal fine particles in the processing area), they are merged into a global associated event.

[0097] As shown in Table 1, its associated events can be expressed as follows.

[0098] Table 1 Schematic table of related events

[0099]

[0100] In the content shown in Table 1, the data example of the frequent item set in the corresponding combination of the preset association rules is pointed out. This data example will be represented as the content represented by the matching polynomial, and the data example will be located on the coal feature vector and the operation feature vector corresponding to the data after subsequent processing. The coal feature vector and the operation feature vector are output to the relevant content using the association model to obtain the final association strength value to be expressed, as well as the data processed by the association model.

[0101] When the fault tree is used for analysis, the basic events of the analysis are extracted from the corresponding content of the associated events. When the association model outputs the association strength value, the associated events it can contain are regarded as basic events, and the basic events are connected to represent the content output by the fault tree.

[0102] Calculate the occurrence probability of each basic event in the fault tree, and use logic gates to calculate the fault probability of the top-level event layer by layer, select the top-level event with the maximum fault probability, and output the basic event combination corresponding to the top-level event to obtain the output fault type.

[0103] The probability of occurrence of each basic event in the fault tree is expressed as: ;in, Represents the basic events in the fault tree The probability of occurrence, j represents the index of the basic event, and the value range of j is 1 to J; k represents the slope parameter of the logic function, which controls the steepness of the probability curve. The larger the value, the steeper the transition from low to high probability, and The higher the sensitivity of the surrounding area, It represents the association degree value of the i-th state recognition area in the association model. This value represents the output result of the association model. The value range of i is 1 to Z. Represents basic events The trigger threshold of the basic event is the calculated value of the corresponding matching polynomial to indicate the relative importance of the basic event. Represents an exponential constant.

[0104] At this time, the probability value that can be represented by each basic event divided in the fault tree can be obtained. This probability value will represent the final calculation result of the data identified on the current conveyor belt. When the fault probability of the top-level event is calculated using the logic gate, the logic gate is divided into the AND gate and the OR gate, and the results of the two calculations will be different; for the top-level event of the AND gate, all the basic events connected with the AND gate under the top-level event are multiplied to represent the conditional probability that these basic events meet at the same time; the OR gate represents the union of two basic events, such as using 1 minus the probability of occurrence of the basic event connected with the OR gate, and multiplying the subtracted value, and then using 1 minus the multiplied value again to represent the probability of the top-level event of all basic events connected with the OR gate; then select the part with the largest value in the top-level event of all basic event combinations under these two calculations to obtain a maximum fault probability, which will indicate that the basic event connected with the logic gate is most likely to fail, and according to the fault type corresponding to the maximum fault probability, the most likely fault of the current conveyor belt can be known, and finally, relevant preparations can be made for the current conveyor belt according to this fault type to reduce the loss caused by the fault.

[0105] For example, the top event of the fault tree under analysis was selected as a conveyor belt break in a certain situation.

[0106] Intermediate events are represented as: long-term wear (triggered by basic event E5: cumulative running time > 1000h); instantaneous overload (triggered by basic event AE1: jam warning event).

[0107] The logic gate connection is expressed as: conveyor belt breakage = long-term wear AND (instantaneous overload OR material fatigue); material fatigue = abnormal temperature event E3 AND speed fluctuation > 20%.

[0108] The input data are: E5: cumulative running time = 1200h, AE1: jam warning event (triggered), E3: temperature = 65°C and speed fluctuation = 25%.

[0109] Then the corresponding data is calculated, such as the probability of long-term wear: P(E5)=1P(E5)=1 (because the running time is >1000h).

[0110] Probability of instantaneous overload: P(AE1)=0.9P(AE1)=0.9.

[0111] Material fatigue probability: P(E3)×P(speed fluctuation)=0.98×0.95=0.93P(E3)×P(speed fluctuation)=0.98×0.95=0.93.

[0112] Finally, the top-level event probability is obtained: P(fracture)=P(long-term wear)×[P(instantaneous overload)+P(material fatigue)−P(instantaneous overload)P(material fatigue)]=1×[0.9+0.93−0.9×0.93]=0.993P(fracture)=P(long-term wear)×[P(instantaneous overload)+P(material fatigue)−P(instantaneous overload)P(material fatigue)]=1×[0.9+0.93−0.9×0.93]=0.993.

[0113] According to the top event probability output by the final selection, the main basic events are found, and these basic events are combined and output together with the fault type described by the top event. After judging these contents, the processing method required for the current conveyor belt is obtained.

[0114] Finally, a relevant table of basic event combinations is obtained, as shown in Table 2.

[0115] Table 2 Basic event combination diagram

[0116]

[0117] Table 2 describes the output of the basic events after the fault tree is used. It also explains the possible combination of related problems under the correlation strength when the coal feature vector and the operation feature vector are output using the correlation model corresponding to the correlation strength and the correlation events corresponding to the correlation strength. The relevant content is subsequently processed according to the problem combination to improve the safety of coal washing.

[0118] In one embodiment of the present invention, the risk weight of the fault type is determined according to the relative connection relationship between each basic event in the fault tree to determine the risk weight of the currently identified fault type, and then a solution search is performed in the database according to this risk weight to find the corresponding fault handling solution.

[0119] The implementation method of the fault processing module includes obtaining a basic event combination corresponding to the fault type, and calculating the periodic probability and expected loss value of each basic event in the basic event combination in the database.

[0120] The periodic probability of each basic time is expressed by extracting its occurrence times from the database, and dividing its occurrence times by the total number of failures in the maintenance cycle to obtain the periodic probability of failure of the basic event, to indicate whether the basic event will have corresponding failures under different maintenance conditions and usage time.

[0121] The expected loss value represents the mean square error of the periodic probability of the corresponding basic event under multiple maintenance cycles, which is used to represent the distribution of the probability of occurrence of each basic event in different cycles.

[0122] Set the risk weight of the current fault type according to the periodic probability and expected loss value of each basic event.

[0123] As for the risk weight, the basic event combination is divided into multiple minimum cut sets according to the connection relationship of each basic event, and the risk weight of the minimum cut set is set to obtain the risk weight of the final output fault type.

[0124] The implementation method of setting the risk weight of the current fault type includes: using the period probability and expected loss value of each basic event to set the risk weight of each basic event. The risk weight of each basic event is expressed as the product of the corresponding period probability and the expected loss value.

[0125] Get the minimum cut set of basic event combinations of the current fault type. Each minimum cut set represents a set of basic events connected from the top event to the specific basic event using the AND gate. Their common occurrence will trigger the top event. Use the risk weight of each basic event to calculate the risk weight of the current minimum cut set. The risk weight in the minimum cut set is obtained based on the product sum of the risk weights of each basic event. Set the sum of the risk weights of the minimum cut set as the risk weight of the fault type.

[0126] Use the risk weight of the current fault type to search the database for solutions and obtain the fault handling solution.

[0127] When searching for solutions, the risk weight of the fault type is used as the first calculation method. First, the correlation coefficient between the risk weight of the fault type and the preset risk weight in the database is calculated. Then, the correlation coefficient is calculated according to the risk weight of the minimum cut set under the current fault type and the preset risk weight as the second calculation method. Finally, the correlation coefficient is calculated between each basic event in the minimum cut set and the preset risk weight as the third calculation method. The correlation coefficient calculated at this time is calculated using the Pearson correlation coefficient. Then, the correlation coefficients corresponding to the first calculation method, the second calculation method, and the third calculation method are sorted from large to small. When sorting at this time, if the correlation coefficient values ​​in the second calculation method are the same, the correlation coefficient values ​​of the third calculation method are sorted. Then, when the correlation coefficients of the first calculation method, the second calculation method, and the third calculation method are all maximum values, the corresponding processing scheme is output as the fault processing scheme.

[0128] The preset risk weights described will be set according to the fault described by the fault type and the fault described by each basic event to determine which specific processing method the current fault type prefers. Ultimately, the conveyor belt can be quickly identified and processed to improve the conveying efficiency of the conveyor belt.

[0129] Although the embodiments of the present invention have been shown and described above, it is to be understood that the above embodiments are exemplary and are not to be construed as limitations on the present invention. A person skilled in the art may make changes, modifications, substitutions and variations to the above embodiments within the scope of the present invention and they are still covered by the protection scope of the present invention.

Claims

1. An intelligent control system for conveyor belt based on coal washing, characterized in that: include: The data acquisition module is used to collect the state information, coal flow rate and conveyor belt speed of the conveyor belt during operation as the operation characteristic vector of the conveyor belt; the coal moisture and coal particle size distribution are used as the coal characteristic vector related to the coal; The state segmentation module is used to divide the conveyor belt into multiple feature units according to the coal feature vectors and operation feature vectors at different positions during coal selection and washing, and to set multiple state recognition areas according to the feature thresholds of the coal feature vectors and operation feature vectors under each feature unit; An operation monitoring module is used to monitor data of multiple state recognition areas, generate multiple characteristic curves according to coal characteristic vectors and operation characteristic vectors, analyze the characteristic curves, and identify the correlation model between the coal characteristic vectors and the operation characteristic vectors; The associated load module is used to determine the degree of association during coal washing according to the association model of the coal characteristic vector and the operation characteristic vector; verify the fault type of each associated event under the corresponding degree of association, and output the basic event combination corresponding to the fault type; The fault handling module is used to determine the risk weight corresponding to the fault type according to the acquired fault type, and check the handling solutions existing in the database to obtain the fault handling solution corresponding to the current fault type.

2. According to claim 1, a conveyor belt intelligent control system based on coal washing is characterized in that: The implementation of running feature vectors also includes: According to the state information at each sampling moment, the obtained coal flow rate and the conveyor belt speed are associated, and a first difference between the coal flow rate and the preset coal flow rate and a second difference between the conveyor belt speed and the preset conveyor belt speed are calculated respectively. After converting the first difference and the second difference into a ratio, the product corresponding to the first difference and the second difference is obtained as the associated value of the coal flow rate and the conveyor belt speed; The average value of the correlation value between coal flow and conveyor belt speed under the same state information is calculated, and the average value is used as the eigenvalue of the operation eigenvector.

3. The intelligent control system for conveyor belt based on coal washing according to claim 1 is characterized in that: The implementation of coal feature vector also includes: According to the coal moisture and coal particle size distribution at each sampling moment, the maximum coal moisture, the maximum coal particle size distribution, the average coal moisture and the average coal particle size distribution are obtained, and the moisture similarity index between the maximum coal moisture and the average coal moisture and the particle size similarity index between the maximum coal particle size distribution and the average coal particle size distribution are calculated respectively; the weighted sum of the moisture similarity index and the particle size similarity index is used as the correlation value of the coal moisture and the coal particle size distribution; The average value of the correlation value between coal moisture and coal particle size distribution under the same state information is calculated, and the average value is used as the eigenvalue of the coal eigenvector.

4. The intelligent control system for conveyor belt based on coal washing according to claim 1 is characterized in that: The implementation of the state segmentation module includes: According to the location of the conveyor belt, the coal characteristic vectors and the operation characteristic vectors in the feeding area, the processing area and the discharging area are determined in sequence, and the conveyor belt is divided into multiple characteristic units; Identify the main component vectors of the coal feature vector and the operation feature vector on each feature unit, and select the feature thresholds of the coal feature vector and the operation feature vector according to the values ​​of the main component vectors; The characteristic thresholds of the coal characteristic vector and the operation characteristic vector are used to define the characteristic units, which are defined as the normal working area, the early warning area and the fault area in turn; the defined characteristic units are used as the output state recognition area.

5. The intelligent control system for conveyor belt based on coal washing according to claim 4 is characterized in that: When the defined feature unit is used as the state recognition area of ​​the output, it also includes: Extracting the characteristic value corresponding to the correlation value of the coal flow rate and the conveyor belt speed on the defined characteristic unit as the first boundary condition; Extracting characteristic values ​​corresponding to the correlation values ​​of coal moisture and coal particle size distribution on the defined characteristic unit as the second boundary condition; According to the first boundary condition and the second boundary condition, boundary processing is performed on the state recognition area to determine the distribution position of each state recognition area.

6. The intelligent control system for conveyor belt based on coal washing according to claim 1 is characterized in that: The implementation methods of the operation monitoring module include: According to the type of the state identification area, the coal characteristic vector and the operation characteristic vector in the state identification area are standardized to obtain at least one standard sample information, and a plurality of characteristic curves are generated according to the value of each standard sample information; Construct a relationship list for each characteristic curve, and use the relationship list to extract candidate frequent item sets; The candidate frequent item sets are matched with the preset association rules, the matching results of the candidate frequent item sets and the preset association rules are obtained, and a matching polynomial corresponding to the matching result is generated, and the association model is set according to the matching polynomial.

7. The intelligent control system for conveyor belt based on coal washing according to claim 6 is characterized in that: When obtaining the matching results of candidate frequent item sets and preset association rules, it also includes: When a candidate frequent item set meets all the conditions of the preset association rule, it is considered that the frequent item set matches the preset association rule successfully. It is determined whether there is a successfully matched adjacent candidate frequent item set in the corresponding state recognition area of ​​the current candidate frequent item set. If so, the adjacent candidate frequent item sets corresponding to the current candidate frequent item set are merged and output as the matching result between the candidate frequent item set and the preset association rule.

8. The intelligent control system for conveyor belt based on coal washing according to claim 1 is characterized in that: The implementation of the associated load module includes: Extract the correlation strength output by the correlation model of the coal feature vector and the operation feature vector, and obtain the correlation events corresponding to the correlation degree. Take the fault type as the top-level event, take each correlation event as the basic event, and connect the basic events to form a logic gate to complete the establishment of the fault tree. Calculate the occurrence probability of each basic event in the fault tree, and use logic gates to calculate the fault probability of the top-level event layer by layer, select the top-level event with the maximum fault probability, and output the basic event combination corresponding to the top-level event to obtain the output fault type.

9. The intelligent control system for conveyor belt based on coal washing according to claim 1 is characterized in that: The implementation method of the fault processing module includes obtaining a basic event combination corresponding to the fault type, and calculating the periodic probability and expected loss value of each basic event in the basic event combination in the database; According to the periodic probability and expected loss value of each basic event, set the risk weight of the current fault type; Use the risk weight of the current fault type to search the database for solutions and obtain the fault handling solution.

10. The intelligent control system for conveyor belt based on coal washing according to claim 9, characterized in that: The implementation methods for setting the risk weight of the current fault type include: Use the periodic probability and expected loss value of each basic event to set the risk weight of each basic event. The risk weight of each basic event is expressed as the product of the corresponding periodic probability and the expected loss value. Obtain the minimum cut set of basic event combinations for the current fault type, use the risk weight of each basic event to calculate the risk weight of the current minimum cut set, and obtain the risk weight within the minimum cut set based on the product and sum of the risk weights of each basic event; set the sum of the risk weights of the minimum cut set as the risk weight of the fault type.

Images