Apriori-based feedback adjustment method and system for technological control parameters of coal mining face

Abstract

The present application provides a feedback adjustment method and system for coal mining face process control parameters based on Apriori. The method includes: obtaining the change values of the coal mining face process control parameters according to the historical production data of the coal mining face included in the established historical time series database of the coal mining face; discretizing the change values of the coal mining face process control parameters based on the Kmeans method to obtain a discrete database of the coal mining face process control parameters; using the Apriori association rule algorithm to solve the change values of the process control parameters in the discrete database and extracting the association rules for feedback adjustment of the coal mining face process control parameters; generating an association rule library between the equipment adjustment parameters and the production adjustment parameters in the coal mining face process control parameters according to the confidence of the extracted association rules and the predefined rules, so as to realize adjusting the equipment parameters to control the change of the production target and guide the production of the coal mine.

Description

Technical Field

[0001] This application relates to the field of mining technology, and particularly to a feedback adjustment method and system for the process control parameters of a coal mining face based on Apriori. Background Art

[0002] With the advancement of the working face and the changes in the working face environmental factors, the process control parameters of the generating equipment will also fluctuate, which will cause the production targets formulated according to the production plan to not be controlled within the expected range, thereby reducing the production efficiency of the fully mechanized coal mining face.

[0003] In actual production operations, in response to the changes in the working site, production technicians will gradually adjust the process control parameters of each equipment according to their experience until the production target returns to the expected range. This online test method of multiple adjustments is time-consuming and laborious, and the operations of production technicians cannot be effectively stored to guide operations at other sites.

[0004] Therefore, there is an urgent need to provide a technical solution to address the deficiencies of the above-mentioned existing technologies. Summary of the Invention

[0005] The purpose of this application is to provide a feedback adjustment method and system for the process control parameters of a coal mining face based on Apriori to solve or alleviate the problems existing in the above-mentioned existing technologies.

[0006] To achieve the above purpose, this application provides the following technical solutions:

[0007] This application provides a feedback adjustment method for the process control parameters of a coal mining face based on Apriori, including: obtaining the change value of the process control parameters of the coal mining face according to the historical time series data of the coal mining face included in the established historical time series database of the coal mining face; wherein, the historical time series data is the historical production data of the coal mining face; discretizing the change value of the process control parameters of the coal mining face based on the Kmeans method to obtain a discrete database of the process control parameters of the coal mining face; using the Apriori association rule algorithm to solve the change value of the discretized process control parameters in the discrete database, and extracting the association rules for the feedback adjustment of the process control parameters of the coal mining face; generating an association rule library of the process control parameters of the coal mining face based on the confidence of the extracted association rules and predefined rules.

[0008] Preferably, obtaining the change value of the process control parameter of the coal mining face based on the historical time-series data of the coal mining face included in the established historical time-series database of the coal mining face specifically includes: taking the difference between adjacent historical time-series data in the historical time-series database to obtain the change value of the process control parameter of the coal mining face under the corresponding working condition.

[0009] Preferably, discretizing the change value of the process control parameter of the coal mining face based on the Kmeans method to obtain the discrete database of the process control parameter of the coal mining face specifically includes: performing cluster analysis on the change value of the process control parameter based on the Kmeans method; discretizing the change value of the process control parameter of the coal mining face according to the cluster analysis result of the change value of the process control parameter to obtain the discrete database of the process control parameter of the coal mining face.

[0010] Preferably, using the Apriori association rule algorithm to solve the discretized change value of the process control parameter in the discrete database and generate the association rule for feedback adjustment of the process control parameter of the coal mining face, including: performing cluster analysis on the change value of the process control parameter of the coal mining face based on the Kmeans method to obtain the cluster interval of the change value of the process control parameter of the coal mining face;

[0011] Scanning all events of the discretized change value of the process control parameter of the coal mining face in the discrete database; wherein, the event is a set of support degrees of the discretized change value of the process control parameter of the coal mining face belonging to the cluster interval;

[0012] Calculating the support degree of each event in sequence and generating a first candidate item set according to the support degree of each event; wherein, the first candidate item set represents a set of support degrees of the process control parameter corresponding to each single event in the coal mining face;

[0013] Performing pruning processing on the first candidate item set to obtain a first frequent item set; wherein, the first frequent item set represents a set of support degrees of the process control parameter corresponding to a single event in the coal mining face that is greater than the preset minimum support degree;

[0014] Generating a second candidate item set by connecting the data in the first frequent item set; wherein, the second candidate item set represents a set of support degrees of the process control parameter corresponding to two associated events in the coal mining face;

[0015] Prune the second candidate item set to obtain the second frequent item set; wherein, the second frequent item set represents a set of support degrees of process control parameters corresponding to two associated events in the coal mining face that are greater than the minimum support degree.

[0016] Generate a third candidate item set by joining the first frequent item set and the second frequent item set, and prune the third candidate item set to obtain the third frequent item set; wherein, the third candidate item set represents a set of support degrees of process control parameters corresponding to three associated events in the coal mining face; the third frequent item set represents a set of support degrees of process control parameters corresponding to three associated events in the coal mining face.

[0017] Preferably, the specific calculation of the support degree of each event is as follows:

[0018] According to:

[0019]

[0020] Calculate the support degree of each event.

[0021] Among them, P({A i}) is the support degree of the event composed of the change values of the process control parameters of the coal mining face belonging to the i-th clustering interval, i = (1, 2,..., n), n is the number of clustering intervals, and n is a positive integer; A represents the process control parameters of the coal mining face; Support_count(A i ) represents the number of change values of the process control parameters of the coal mining face belonging to the i-th clustering interval; Total_count represents the number of all events.

[0022] Preferably, the pruning process for the first candidate item set to obtain the first frequent item set is specifically: compare the support degrees of each event in the first candidate item set with the minimum support degree respectively, and the data corresponding to the events greater than or equal to the minimum support degree constitute the first frequent item set.

[0023] Preferably, based on the confidence of the extracted association rules and predefined rules, generating an association rule library for the process control parameters of the coal mining face is specifically: calculate the confidence of each association rule for the feedback adjustment of the extracted process control parameters of the coal mining face; compare the confidence of each association rule with the preset minimum confidence, and the association rules greater than or equal to the minimum support degree and greater than or equal to the minimum confidence constitute the association rule library.

[0024] Preferably, the confidence of each of the association rules for the feedback regulation of the coal mining face process control parameters extracted by the calculation is specifically: According to:

[0025]

[0026] Calculate the confidence of the extracted association rules;

[0027] Wherein, Confidence(B j →C j ) is the confidence of the associated process control parameter B j and the process control parameter C j ; Support_count(B j ∪C j ) is the number of change values of the associated process control parameter B j and the process control parameter C j belonging to the j-th clustering interval; Support_count(B j ) represents the number of change values of the process control parameter B j of the coal mining face belonging to the j-th clustering interval; j = (1, 2,..., n), n is the number of the clustering intervals, and n is a positive integer.

[0028] Preferably, the historical time series data of the coal mining face includes: the change values of the shearer traction speed, the hydraulic support moving speed, the scraper conveyor rotation speed, the transfer conveyor rotation speed, the outlet pressure of the first emulsion pump, the outlet pressure of the second emulsion pump, the outlet pressure of the first spray pump, the outlet pressure of the second spray pump, and the coal production per unit time.

[0029] The embodiment of the present application further provides a feedback regulation system for coal mining face process control parameters based on Apriori, including: a data sampling unit configured to obtain the change values of the coal mining face process control parameters according to the historical time series data of the coal mining face included in the established historical time series database of the coal mining face; wherein, the historical time series data is the historical production data of the coal mining face; a data discretization unit configured to discretize the change values of the coal mining face process control parameters based on the Kmeans method to obtain a discrete database of the coal mining face process control parameters; a rule extraction unit configured to use the Apriori association rule algorithm to solve the change values of the discretized process control parameters in the discrete database and extract the association rules for the feedback regulation of the coal mining face process control parameters; a rule base generation unit configured to generate an association rule base of the coal mining face process control parameters based on the confidence of the extracted association rules and a predetermined rule.

[0030] Beneficial effects:

[0031] In the feedback adjustment technology of coal mining face process control parameters based on Apriori provided by this application, first, according to the historical time-series data of the coal mining face contained in the established historical time-series database of the coal mining face, the change value of the coal mining face process control parameters is obtained; then, based on the Kmeans method, the change value of the coal mining face process control parameters is discretized to obtain the discrete database of the coal mining face process control parameters; next, the Apriori association rule algorithm is used to solve the change value of the discretized process control parameters in the discrete database, and the association rules for feedback adjustment of the coal mining face process control parameters are extracted; finally, according to the confidence of the extracted association rules, based on the predefined rules, the association rule library of the coal mining face process control parameters is generated. Thereby, it is possible to control the process control parameters based on the adjustment rules of the coal mining face process control parameters as the coal mining face advances and the working face environmental factors change, so as to effectively control the actual production target within the expected range according to the production target set by the production plan, improve the production efficiency of the coal mining face, and ensure the normal operation of the coal mining face. Description of the drawings

[0032] The specification drawings forming a part of this application are used to provide a further understanding of this application. The schematic embodiments of this application and their descriptions are used to explain this application and do not constitute an improper limitation of this application. Among them:

[0033] Figure 1 It is a schematic flowchart of a method for feedback adjustment of coal mining face process control parameters based on Apriori provided by some embodiments of this application;

[0034] Figure 2 It is a schematic logical diagram for generating an association rule library provided by some embodiments of this application;

[0035] Figure 3 It is a schematic structural diagram of a system for feedback adjustment of coal mining face process control parameters based on Apriori provided by some embodiments of this application. Detailed implementation manners

[0036] The present application will be described in detail below with reference to the accompanying drawings and in conjunction with embodiments. Each example is provided by way of explanation of the present application rather than limiting the present application. In fact, those skilled in the art will appreciate that modifications and variations can be made to the present application without departing from the scope or spirit thereof. For example, features shown or described as part of one embodiment can be used in another embodiment to yield yet another embodiment. Accordingly, it is intended that the present application cover such modifications and variations that fall within the scope of the appended claims and their equivalents.

[0037] In coal mine coal mining production operations, the method of gradually adjusting the process control parameters of equipment by production technicians according to their respective experiences has a limited scope of adaptation and cannot form a systematic and effective guidance for equipment adjustment during coal mine mining. For this reason, the applicant has proposed a feedback adjustment technology for process control parameters of a coal mining face based on Apriori. From the historical production data of the coal mining face, the variation rules of the process control parameters of the coal mining face with the advancement of the coal mining face and the changes in the working face environmental factors are mined, and then scientific guidance for actual production is provided, facilitating the timely correction of fluctuations in process control parameters caused by changes in the working environment.

[0038] First of all, it should be noted that the process control parameters in the present application include equipment adjustment parameters and production adjustment parameters. The association rule of the process control parameters is the relationship between the equipment adjustment parameters and the production adjustment parameters. The adjustment of the process control parameters includes the adjustment of equipment parameters and the adjustment of production targets.

[0039] As Figure 1 shown, the feedback adjustment method for process control parameters of a coal mining face based on Apriori includes:

[0040] Step S101: Obtain the change values of the process control parameters of the coal mining face according to the historical time-series data of the coal mining face included in the established historical time-series database of the coal mining face.

[0041] Among them, the historical time-series data is the historical production data of the coal mining face.

[0042] In the present application, the historical time-series data of the coal mining face mainly includes: the change values of the shearer traction speed, the hydraulic support moving speed, the scraper conveyor rotation speed, the transfer conveyor rotation speed, the outlet pressure of the first emulsion pump, the outlet pressure of the second emulsion pump, the outlet pressure of the first spray pump, the outlet pressure of the second spray pump, and the coal production per unit time. Specifically, the equipment parameters are collected through sensors arranged on-site during the coal mine production process to obtain the historical production data of the coal mining face.

[0043] In this application, the shearer traction speed is represented by PSS, with the unit of m / min; the hydraulic support moving speed is represented by HSMS, with the unit of frames / min; the scraper conveyor rotation speed is represented by CSSC, with the unit of r / min; the transfer conveyor rotation speed is represented by CSSL, with the unit of r / min; the outlet pressure of the first emulsion pump is represented by EPOP1, with the unit of Mpa; the outlet pressure of the second emulsion pump is represented by EPOP2, with the unit of Mpa; the outlet pressure of the first spray pump is represented by SPOP1, with the unit of Mpa; the outlet pressure of the second spray pump is represented by SPOP2, with the unit of Mpa; the change value of the coal production per unit time is represented by OCPM, with the unit of t / min.

[0044] In this application, the historical production data of the coal mining face is time-series data. In a specific example, the historical production data is shown in Table 1 as follows:

[0045] Table 1 Historical production data

[0046]

[0047] When obtaining the change values of the process control parameters of the coal mining face from the historical time-series data of the coal mining face, the adjacent historical time-series data in the historical time-series database are subtracted to obtain the change values of the process control parameters of the coal mining face under the corresponding working conditions. In the example shown in Table 1, the change values of the process control parameters are shown in Table 2 as follows:

[0048] Table 2 Change values of process control parameters

[0049]

[0050] Among them, the change values of the process control parameters include: the change value of the shearer traction speed (ΔPSS), the change value of the hydraulic support moving speed (ΔHSMS), the change value of the scraper conveyor rotation speed (ΔCSSC), the change value of the transfer conveyor rotation speed (ΔCSSL), the change value of the outlet pressure of the first emulsion pump (ΔEPOP1), the change value of the outlet pressure of the second emulsion pump (ΔEPOP2), the change value of the outlet pressure of the first spray pump (ΔSPOP1), the change value of the outlet pressure of the second spray pump (ΔSPOP2), and the change value of the production target is (ΔOCPM).

[0051] Step S102: Based on the Kmeans method, discretize the change values of the process control parameters of the coal mining face to obtain the discrete database of the process control parameters of the coal mining face.

[0052] In this application, in the database of the change values of the process control parameters (change value database), the change values of the process control parameters have different dimensions and value ranges, and cannot be divided into equal intervals or equal frequencies. Therefore, the change values of the process control parameters are discretized based on the Kmeans method.

[0053] Specifically, first, based on the Kmeans method, cluster analysis is performed on the change values of the process control parameters in the change value database; then, according to the cluster analysis results of the change values of the process control parameters, the change values of the process control parameters of the coal mining face are discretized to obtain the discrete database of the process control parameters of the coal mining face.

[0054] In this application, first, in the data space composed of all the data in the change value database, k (k is a positive integer) samples c = (c1, c2,..., c k ) are randomly selected as the initial cluster centers of the data space; then, the Euclidean distances from each sample x = (x1, x2,..., x i ) in the data space to the cluster center c are calculated respectively, and the samples closest to each cluster center are grouped into one category to form k cluster clusters; then, the mean cluster centers of the k cluster clusters are used as the new cluster centers of the data space, and the above steps are continuously cycled until the new cluster centers of the data space no longer change. Thus, the k formed cluster centers are the breakpoints for discretizing the continuous data.

[0055] In the specific example shown in Table 1, each process control parameter is divided into 4 intervals, and the Kmeans clustering algorithm is used to cluster the data in the change value database. The clustering interval results are shown in Table 3 as follows:

[0056] Table 3 Clustering Results

[0057]

[0058]

[0059] Furthermore, according to the clustering results, the change values shown in Table 2 are converted into discrete data, and the conversion results are shown in Table 4 as follows:

[0060] Table 4 Discrete Data

[0061]

[0062] Step S103: Use the Apriori association rule algorithm to solve the change values of the discretized process control parameters in the discrete database, and extract the association rules for the feedback adjustment of the process control parameters of the coal mining face.

[0063] In this application, first, based on the Kmeans method, cluster analysis is performed on the change values of the process control parameters of the coal mining face to obtain the clustering intervals of the change values of the process control parameters of the coal mining face; then, scan all events of the change values of the process control parameters of the discretized coal mining face in the discrete database; where an event is a set of change values of the process control parameters of the discretized coal mining face that belong to the clustering interval; then, calculate the support degree of each event in turn, and generate the first candidate item set according to the support degree of each event; where the first candidate item set represents the set of support degrees of the process control parameters corresponding to each single event in the coal mining face; then, perform pruning processing on the first candidate item set to obtain the first frequent item set; where the first frequent item set represents the set of support degrees of the process control parameters corresponding to single events in the coal mining face that are greater than the preset minimum support degree; then, generate the second candidate item set by connecting the data in the first frequent item set; where the second candidate item set represents the set of support degrees of the process control parameters corresponding to two related events in the coal mining face; then, perform pruning processing on the second candidate item set to obtain the second frequent item set; where the second frequent item set represents the set of support degrees of the process control parameters corresponding to two related events in the coal mining face that are greater than the minimum support degree; finally, generate the third candidate item set by connecting the first frequent item set and the second frequent item set, and perform pruning processing on the third candidate item set to obtain the third frequent item set; where the third candidate item set represents the set of support degrees of the process control parameters corresponding to three related events in the coal mining face; the third frequent item set represents the set of support degrees of the process control parameters corresponding to three related events in the coal mining face.

[0064] In this application, according to the formula:

[0065]

[0066] Calculate the support degree of each event. Where P({A i}) is the support degree of the event composed of the change values of the process control parameters of the coal mining face belonging to the i-th clustering interval, i = (1, 2,..., n), n is the number of clustering intervals, and n is a positive integer; A represents the process control parameters of the coal mining face; Support_count(A i ) represents the number of change values of the process control parameters of the coal mining face belonging to the i-th clustering interval; Total_count represents the number of all events.

[0067] In the specific example shown in Table 1, as Figure 2 shown, by scanning all events in the discrete database, calculate the support degree of each item set in turn. For example, the calculation result of the support degree Support({A1}) of {A1} is as follows:

[0068]

[0069] According to the calculation results, the first candidate item set C1 is generated, as shown in Table 5. Table 5 is as follows:

[0070] Table 5 The first candidate item set C1

[0071]

[0072] The first frequent item set L1 is obtained from the first candidate item set C1 through a pruning step. By comparing the support degrees of each event in the first candidate item set with the minimum support degree respectively, the data corresponding to the events greater than or equal to the minimum support degree constitutes the first frequent item set. Specifically, the minimum support degree is set to 40%. The item sets in the first candidate item set C1 are compared with the minimum support degree, the item sets less than the minimum support degree are removed, and the item sets greater than or equal to the minimum support degree are retained to generate the first frequent item set L1, as shown in Table 6. Table 6 is as follows:

[0073] Table 6 The first frequent item set L1

[0074]

[0075] Then, the data in the first frequent item set L1 is passed through a joining step (joining the data L a-1 and the data L a to generate the candidate item set C a+1 , where a ≥ 2) to generate the second candidate item set C2, as shown in Table 7; then, through the pruning step, the item sets in the second candidate item set C2 are compared with the minimum support degree, the item sets less than the minimum support degree are removed, and the item sets greater than or equal to the minimum support degree are retained to generate the second frequent item set L2, as shown in Table 8. Tables 7 and 8 are as follows:

[0076] Table 7 The second candidate item set C2

[0077]

[0078] Table 8 The second frequent item set L2

[0079]

[0080] Finally, the first frequent item set L1 and the second frequent item set L2 are joined through a joining step to generate the third candidate item set C3, as shown in Table 9. By comparing the set minimum support degree through the pruning step, the item sets less than the minimum support degree in the third candidate item set C3 are removed, and the item sets greater than or equal to the minimum support degree are retained to generate the third frequent item set L3, as shown in Table 10.

[0081] Table 9 The third candidate item set C3

[0082]

[0083] Table 10 Third Most Frequent Item Set L3

[0084]

[0085] Step S104. Based on the confidence of the extracted association rules and predefined rules, generate an association rule library for the process control parameters of the coal mining face.

[0086] Specifically, calculate the confidence of each association rule for the feedback adjustment of the process control parameters of the coal mining face; compare the confidence of each association rule with the preset minimum confidence, and form an association rule library with the association rules whose support is greater than or equal to the minimum support and confidence is greater than or equal to the minimum confidence.

[0087] In this application, according to the formula:

[0088]

[0089] Calculate the support of each association rule for the feedback adjustment of the process control parameters of the coal mining face.

[0090] Among them, Support(B j →C j ) is the support of the associated process control parameter B j and the process control parameter C j of the coal mining face, Support_count(B j ∪C j ) is the number of change values of the associated process control parameter B j and the process control parameter C j belonging to the j-th clustering interval; Total_count is the number of two associated process control parameters, that is, the number of two events with an association relationship.

[0091] According to the formula:

[0092]

[0093] Calculate the confidence of the extracted association rules.

[0094] Among them, Confidence(B j →C j ) is the confidence of the associated process control parameter B j and the process control parameter C j of the coal mining face; Support_count(B j ∪C j) is the associated process control parameter B belonging to the j-th clustering interval j and the process control parameter C j the number of change values; Support_count(B j ) represents the number of change values of the process control parameter B of the coal mining face belonging to the j-th clustering interval j ; j = (1, 2,..., n), where n is the number of clustering intervals and n is a positive integer.

[0095] For example, the calculation process of the confidence Confidence({A2, B2}) is as follows:

[0096]

[0097] In this application, the minimum confidence is set to 80%. The association rules that simultaneously meet both being greater than or equal to the minimum support and greater than or equal to the minimum confidence are extracted as strong association rules. The strong association rules obtained from the specific example shown in Table 1 are shown in Table 11 as follows:

[0098] Table 11 Strong Association Rule Table

[0099]

[0100] Then, the association rule library contains all the strong association rules. Among the strong association rules shown in Table 11,

[0101] Rule 1: A2 → I2: That is, when the change value of the shearer traction speed is within (0.21, 0.89], the change value of the coal production per unit time caused is within (1.97, 8.84]. The support degree of this rule is 60% and the confidence is 100%.

[0102] Rule 2: B2 → I2: That is, when the change value of the hydraulic support moving speed is within (0.07, 0.13], the change value of the coal production per unit time caused is within (1.97, 8.84]. The support degree of this rule is 40% and the confidence is 100%.

[0103] Rule 3: A2 → D1 → I2: That is, when the change value of the shearer traction speed is within (0.21, 0.89] and the change value of the transfer machine rotation speed is within (-0.33, 0], the change value of the coal production per unit time caused is within (1.97, 8.84]. The support degree of this rule is 40% and the confidence is 100%

[0104] Rule 4: A2 → G1 → I2: That is, when the change value of the shearer traction speed is in the range of (0.21, 0.89] and the change value of the outlet pressure of spray pump 1 is in the range of (-0.42, 0], the change value of the coal output per unit time is in the range of (1.97, 8.84]. The support degree of this rule is 40%, and the confidence degree is 100%.

[0105] Rule 5: B2 → A2: That is, when the change value of the hydraulic support moving speed is in the range of (0.07, 0.13], the change value of the shearer traction speed is in the range of (0.21, 0.89]. The support degree of this rule is 40%, and the confidence degree is 100%.

[0106] Rule 6: D1 → I1 → A2: That is, when the change value of the belt conveyor speed is in the range of (-0.33, 0] and the change value of the coal output per unit time is in the range of (0, 1.97], the change value of the shearer traction speed is in the range of (0.21, 0.89]. The support degree of this rule is 40%, and the confidence degree is 100%.

[0107] Rule 7: G1 → I2 → A2: That is, when the change value of the outlet pressure of spray pump 1 is in the range of (-0.42, 0] and the change value of the coal output per unit time is in the range of (1.97, 8.84], the change value of the shearer traction speed is in the range of (0.21, 0.89]. The support degree of this rule is 40%, and the confidence degree is 100%.

[0108] Rule 8: C1 → D1: That is, when the change value of the scraper conveyor speed is in the range of (-0.36, 0], the change value of the belt conveyor speed is in the range of (-0.33, 0]. The support degree of this rule is 40%, and the confidence degree is 80%.

[0109] Rule 9: H4 → D1: That is, when the change value of the outlet pressure of spray pump 2 is in the range of (0.09, 0.24], the change value of the belt conveyor speed is in the range of (-0.33, 0]. The support degree of this rule is 40%, and the confidence degree is 80%.

[0110] In this application, when the actual value of the production target of the coal mining face deviates from the expected value and reaches the set threshold, the production process parameters are adjusted in real time according to the rules in the association rule library. Therefore, through the Apriori algorithm, the association relationship analysis of the coal mining process parameters collected in the coal mining face production system is carried out, corresponding management rules are generated, and the generated association rules are stored in the database, so as to realize that when the actual value of the production target deviates from the expected value and reaches the set threshold, the equipment adjustment parameters are feedback-adjusted in real time according to the rules in the rule library, thereby improving the production efficiency of the coal mining face and ensuring that the coal mining face of the coal mine is in a normal operation state.

[0111] The embodiment of this application also provides a feedback adjustment system for the process control parameters of the coal mining face based on Apriori, as Figure 3As shown in the figure, the feedback adjustment system for the technological control parameters of the coal mining face based on Apriori includes: a data sampling unit 301 configured to obtain the change value of the technological control parameters of the coal mining face according to the historical time-series data of the coal mining face included in the established historical time-series database of the coal mining face; wherein the historical time-series data is the historical production data of the coal mining face; a data discretization unit 302 configured to discretize the change value of the technological control parameters of the coal mining face based on the Kmeans method to obtain a discrete database of the technological control parameters of the coal mining face; a rule extraction unit 303 configured to use the Apriori association rule algorithm to solve the change value of the technological control parameters after discretization in the discrete database and extract the association rules for the feedback adjustment of the technological control parameters of the coal mining face; a rule base generation unit 304 configured to generate an association rule base for the technological control parameters of the coal mining face based on the confidence level of the extracted association rules and the predetermined rules.

[0112] The feedback adjustment system for the technological control parameters of the coal mining face based on Apriori provided by the embodiments of the present application can implement the steps and processes of the feedback adjustment method for the technological control parameters of the coal mining face based on Apriori in any of the above embodiments and achieve the same technical effects, which will not be elaborated herein one by one.

[0113] The above are only the preferred embodiments of the present application and are not used to limit the present application. For those skilled in the art, various changes and modifications can be made to the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A feedback adjustment method for the process control parameters of a coal mining face based on Apriori, characterized in that, Including: Obtaining a change value of the process control parameters of the coal mining face according to the historical time-series data of the coal mining face included in the established historical time-series database of the coal mining face; wherein, the historical time-series data is the historical production data of the coal mining face; Based on the Kmeans method, discretizing the change value of the process control parameters of the coal mining face to obtain a discrete database of the process control parameters of the coal mining face; Using the Apriori association rule algorithm to solve the discretized change value of the process control parameters in the discrete database, and extracting the association rules for feedback adjustment of the process control parameters of the coal mining face; Based on the confidence of the extracted association rules and predefined rules, generating an association rule library of the process control parameters of the coal mining face.

2. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to claim 1, characterized in that, The obtaining a change value of the process control parameters of the coal mining face according to the historical time-series data of the coal mining face included in the established historical time-series database of the coal mining face is specifically: Taking the difference between adjacent historical time-series data in the historical time-series database to obtain a change value of the process control parameters of the coal mining face under the corresponding working conditions.

3. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to claim 1, wherein, The based on the Kmeans method, discretizing the change value of the process control parameters of the coal mining face to obtain a discrete database of the process control parameters of the coal mining face is specifically: Based on the Kmeans method, performing cluster analysis on the change value of the process control parameters; According to the cluster analysis result of the change value of the process control parameters, discretizing the change value of the process control parameters of the coal mining face to obtain a discrete database of the process control parameters of the coal mining face.

4. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to claim 1, characterized in that, The using the Apriori association rule algorithm to solve the discretized change value of the process control parameters in the discrete database and generating the association rules for feedback adjustment of the process control parameters of the coal mining face includes: Based on the Kmeans method, performing cluster analysis on the change value of the process control parameters of the coal mining face to obtain a cluster interval of the change value of the process control parameters of the coal mining face; Scanning all events of the discretized change value of the process control parameters of the coal mining face in the discrete database; wherein, the event is a set of support degrees of the discretized change value of the process control parameters of the coal mining face belonging to the cluster interval; Sequentially calculating the support degree of each event, and generating a first candidate item set according to the support degree of each event; wherein, the first candidate item set represents a set of support degrees of the process control parameters corresponding to each single event in the coal mining face; Performing pruning processing on the first candidate item set to obtain a first frequent item set; wherein, the first frequent item set represents a set of support degrees of the process control parameters corresponding to a single event in the coal mining face that is greater than a preset minimum support degree; Generating a second candidate item set by connecting the data in the first frequent item set; wherein, the second candidate item set represents a set of support degrees of the process control parameters corresponding to two associated events in the coal mining face; Prune the second candidate item set to obtain the second frequent item set; wherein, the second frequent item set represents the set of support degrees of the process control parameters corresponding to two associated events in the coal mining face that are greater than the minimum support degree. Generate a third candidate item set by joining the first frequent item set and the second frequent item set, and prune the third candidate item set to obtain the third frequent item set; wherein, the third candidate item set represents the set of support degrees of the process control parameters corresponding to three associated events in the coal mining face; the third frequent item set represents the set of support degrees of the process control parameters corresponding to three associated events in the coal mining face.

5. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to claim 4, characterized in that, Specifically, the calculation of the support degree of each event is as follows: According to: Calculate the support degree of each event. Among them, P({A i}) is the support of the event composed of the change values of the process control parameters of the coal mining face belonging to the i-th clustering interval, where i = (1, 2,..., n), n is the number of the clustering intervals, and n is a positive integer; A represents the process control parameters of the coal mining face; Support_count(A i ) represents the number of change values of the process control parameters of the coal mining face belonging to the i-th clustering interval; Total_count represents the number of all the events.

6. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to claim 4, characterized in that, Specifically, the pruning process of the first candidate item set to obtain the first frequent item set is as follows: Compare the support degrees of each event in the first candidate item set with the minimum support degree respectively, and the data corresponding to the events greater than or equal to the minimum support degree constitute the first frequent item set.

7. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to claim 4, characterized in that, Specifically, based on the confidence of the extracted association rules and predefined rules, generate the association rule library of the process control parameters of the coal mining face as follows: Calculate the confidence of each association rule for the feedback adjustment of the process control parameters of the coal mining face extracted. Compare the confidence of each association rule with the preset minimum confidence, and the association rules greater than or equal to the minimum support degree and greater than or equal to the minimum confidence constitute the association rule library.

8. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to claim 7, characterized in that, Specifically, the calculation of the confidence of each association rule for the feedback adjustment of the process control parameters of the coal mining face extracted is as follows: According to: Calculate the confidence of the extracted association rule. where Confidence(B j →C j ) is the confidence of the associated process control parameter B j and the process control parameter C j ; Support_count(B j ∪C j ) is the number of change values of the associated process control parameter B j and the process control parameter C j belonging to the j-th said clustering interval; Support_count(B j ) represents the number of change values of the process control parameter B j of the coal mining face belonging to the j-th said clustering interval; j = (1, 2,..., n), where n is the number of said clustering intervals and n is a positive integer.

9. The feedback adjustment method for the technological control parameters of the coal mining face based on Apriori according to any one of claims 1-8, characterized in that, The historical time series data of the coal mining face includes: the traction speed of the shearer, the support moving speed of the hydraulic support, the rotating speed of the scraper conveyor, the rotating speed of the loader, the outlet pressure of the first emulsion pump, the outlet pressure of the second emulsion pump, the outlet pressure of the first spray pump, the outlet pressure of the second spray pump, and the change value of the coal production per unit time.

10. A feedback adjustment system for technological control parameters of a coal mining face based on Apriori, characterized in that, Including: A data sampling unit configured to obtain the change values of the process control parameters of the coal mining face according to the historical time series data of the coal mining face included in the established historical time series database of the coal mining face; wherein, the historical time series data is the historical production data of the coal mining face. A data discretization unit configured to discretize the change values of the process control parameters of the coal mining face based on the Kmeans method to obtain the discrete database of the process control parameters of the coal mining face. A rule extraction unit configured to use the Apriori association rule algorithm to solve the change values of the discretized process control parameters in the discrete database and extract the association rules for the feedback adjustment of the process control parameters of the coal mining face. A rule library generation unit configured to generate the association rule library of the process control parameters of the coal mining face based on the confidence of the extracted association rules and predefined rules.

Images