CN113419496A

CN113419496A - Waterproof material production intelligent management and control method and system based on big data statistics

Info

Publication number: CN113419496A
Application number: CN202110752498.7A
Authority: CN
Inventors: 徐晓明; 徐媛; 张小飞; 王龙; 马俊
Original assignee: Changzhou Benefit Waterproof Equipment Co ltd
Current assignee: Changzhou Benefit Waterproof Equipment Co ltd
Priority date: 2021-07-02
Filing date: 2021-07-02
Publication date: 2021-09-21

Abstract

The embodiment of the invention provides a waterproof material production intelligent management and control method and system based on big data statistics, wherein maintenance fault evaluation indexes of a target waterproof material production plan are obtained based on at least two second production link big data, the second production link big data can be reference production link big data, and the characteristic details are richer, so that the accuracy of the maintenance fault evaluation indexes can be improved; and the first target dynamic operation state data sequence is obtained by screening the reference production link big data based on the correlation parameters, so that the reference data volume of the reference production link big data for evaluating the maintenance fault evaluation index of the target waterproof material production plan is simplified, and the first target production link big data screened based on the correlation parameters can obtain the second production link big data which is strongly correlated with the maintenance fault evaluation index of the target waterproof material production plan, so that the evaluation efficiency is further improved.

Description

Waterproof material production intelligent management and control method and system based on big data statistics

Technical Field

The invention relates to the technical field of big data, in particular to a waterproof material production intelligent management and control method and system based on big data statistics.

Background

Under the background of big data, whether the big data technology can be fully utilized by the machine manufacturing is related to the future survival and development of the machine manufacturing, and the big data technology has strong collection, analysis and processing capabilities, however, most enterprises cannot fully utilize the big data to make effective decisions at present. And the production big data of the existing waterproof material manufacturing enterprises lack the current situation of unified management and control.

Disclosure of Invention

In order to overcome at least the above disadvantages in the prior art, the present invention provides a method and a system for intelligent management and control of waterproof material production based on big data statistics.

In a first aspect, the invention provides a waterproof material production intelligent management and control method based on big data statistics, which is applied to an intelligent management and control cloud service platform, wherein the intelligent management and control cloud service platform is in communication connection with a plurality of production intelligent monitoring devices, and the method comprises the following steps:

acquiring first production link big data of each production intelligent monitoring device of a related control subarea of a target waterproof material production plan and maintenance fault evaluation indexes of a previous reference waterproof material production plan of the target waterproof material production plan;

acquiring second production link big data and a target maintenance fault state sequence corresponding to a plurality of reference waterproof material production plans before the target waterproof material production plan; the first production link big data and/or the second production link big data comprise: representing at least one production link big data of production link temperature control data, production link time control data, production link energy consumption control data and production link early warning control data;

determining a first target dynamic operation condition data sequence based on a dynamic operation condition data sequence consisting of the second production link big data and the correlation parameter of the target maintenance fault state sequence, wherein the first target dynamic operation condition data sequence comprises at least two second production link big data referring to a waterproof material production plan;

and determining the maintenance fault evaluation index of the target waterproof material production plan according to the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the waterproof material production plan which is referred to in the front of the target waterproof material production plan and the first target dynamic operation state data sequence.

In a second aspect, an embodiment of the present invention further provides a waterproof material production intelligent management and control system based on big data statistics, where the waterproof material production intelligent management and control system based on big data statistics includes an intelligent management and control cloud service platform and a plurality of production intelligent monitoring devices in communication connection with the intelligent management and control cloud service platform;

the intelligent management and control cloud service platform is used for:

According to any one of the aspects, in the embodiment provided by the invention, the maintenance fault evaluation index of the target waterproof material production plan is obtained based on at least two second production link big data, the second production link big data can be reference production link big data, and compared with a mode of adopting fixed reference production link big data, the method provided by the invention has the advantages that the adopted characteristic details are richer, so that the accuracy of the maintenance fault evaluation index can be improved; moreover, the first target dynamic operation state data sequence is obtained based on the correlation parameter of the target maintenance fault state sequence, namely the first target dynamic operation state data sequence is obtained by screening the reference production link big data based on the correlation parameter, so that the reference data volume of the reference production link big data of the maintenance fault evaluation index for evaluating the target waterproof material production plan is simplified, and the first target production link big data screened based on the correlation parameter can obtain the second production link big data which is strongly correlated with the maintenance fault evaluation index of the target waterproof material production plan, so that the evaluation efficiency is further improved.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that need to be called in the embodiments are briefly described below, it should be understood that the following drawings only illustrate some embodiments of the present invention, and therefore should not be considered as limiting the scope, and for those skilled in the art, other related drawings can be obtained according to the drawings without inventive efforts.

Fig. 1 is a schematic view of an application scenario of a waterproof material production intelligent management and control system based on big data statistics according to an embodiment of the present invention;

fig. 2 is a schematic flow chart of an intelligent management and control method for waterproof material production based on big data statistics according to an embodiment of the present invention;

fig. 3 is a schematic functional module diagram of an intelligent management and control device for waterproof material production based on big data statistics according to an embodiment of the present invention;

fig. 4 is a schematic block diagram of a structure of an intelligent management and control cloud service platform for implementing the intelligent management and control method for waterproof material production based on big data statistics, provided by the embodiment of the present invention.

Detailed Description

The present invention is described in detail below with reference to the drawings, and the specific operation methods in the method embodiments can also be applied to the apparatus embodiments or the system embodiments.

Fig. 1 is an explanatory schematic diagram of a waterproof material production intelligent management and control system 10 based on big data statistics according to an embodiment of the present invention. The waterproof material production intelligent management and control system 10 based on big data statistics may include an intelligent management and control cloud service platform 100 and a production intelligent monitoring device 200 communicatively connected to the intelligent management and control cloud service platform 100. The intelligent management and control system 10 for waterproof material production based on big data statistics shown in fig. 1 is only one possible example, and in other possible embodiments, the intelligent management and control system 10 for waterproof material production based on big data statistics may also include only at least part of the components shown in fig. 1 or may also include other components.

For example, the intelligent management and control cloud service platform 100 and the production intelligent monitoring device 200 in the waterproof material production intelligent management and control system 10 based on big data statistics may cooperatively perform the waterproof material production intelligent management and control method based on big data statistics described in the following method embodiments, and the detailed description of the method embodiments may be referred to in the following steps of the intelligent management and control cloud service platform 100 and the production intelligent monitoring device 200.

In order to solve the technical problem in the foregoing background, referring to fig. 2, a schematic flow chart of a waterproof material production intelligent management and control method based on big data statistics according to an embodiment of the present invention, the waterproof material production intelligent management and control method based on big data statistics according to the embodiment of the present invention may be executed by the intelligent management and control cloud service platform 100 shown in fig. 1, and the waterproof material production intelligent management and control method based on big data statistics is described in detail below.

Step S110, acquiring first production link big data of a related management and control partition of the target waterproof material production plan and maintenance fault evaluation indexes of a waterproof material production plan referenced before the target waterproof material production plan.

In this embodiment, the maintenance fault evaluation index may be used to represent a development trend situation of a maintenance fault of a related management and control partition of the target waterproof material production plan, and the larger the maintenance fault evaluation index is, the higher the maintenance fault rate of the related management and control partition is.

And step S120, acquiring second production link big data and target maintenance fault state sequences corresponding to a plurality of reference waterproof material production plans before the target waterproof material production plan.

Step S130, determining a first target dynamic operation state data sequence based on a correlation parameter of a dynamic operation state data sequence composed of second production link big data and a target maintenance fault state sequence, wherein the first target dynamic operation state data sequence comprises at least two second production link big data referring to a waterproof material production plan.

Step S140, determining a maintenance fault evaluation index of the target waterproof material production plan according to the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the waterproof material production plan which is referred to before the target waterproof material production plan and the first target dynamic operation state data sequence.

The scheme provided by the invention can be applied to but not limited to the following scenes: the method comprises the steps of obtaining first production link big data of a related control subarea of a target waterproof material production plan, maintenance fault evaluation indexes of a previous reference waterproof material production plan of the target waterproof material production plan, second production link big data corresponding to a plurality of reference waterproof material production plans before the target waterproof material production plan and a target maintenance fault state sequence, wherein the target maintenance fault state sequence comprises a plurality of maintenance fault states corresponding to the reference waterproof material production plans, and the maintenance fault states can be represented by identification characters, namely the corresponding maintenance fault state is 1 when a maintenance fault abnormal state exists, and the corresponding maintenance fault state is 0 when the maintenance fault abnormal state does not exist. The waterproof material production plan may be an enabled instance object with certain production plan data, a first target dynamic operation condition data sequence is screened from second production link big data based on correlation parameters of the dynamic operation condition data sequence and a target maintenance fault state sequence, the first target dynamic operation condition data sequence includes second production link big data of at least two reference waterproof material production plans, and the first target dynamic operation condition data sequence may be a sequence formed by production link big data corresponding to a plurality of reference waterproof material production plans associated with the target waterproof material production plan. And then, determining the maintenance fault evaluation index of the target waterproof material production plan based on the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the previous reference waterproof material production plan of the target waterproof material production plan and the first target dynamic operation condition data sequence so as to perform subsequent management and control processing based on the result.

In order to clarify the technical solutions provided by the present invention, the following explains the solutions provided by the present invention by specific examples:

assuming that the target waterproof material production plan is (s +1) waterproof material production plan, the first production link big data of the corresponding related control subarea is represented as Qs +1, the production link big data of the previous waterproof material production plan (i.e. the s waterproof material production plan) of the target waterproof material production plan is represented as Qs, and a plurality of waterproof material production plans are referred before the target waterproof material production plan, the plurality of reference waterproof material production plans may be a plurality of reference waterproof material production plans that are previous to the target waterproof material production plan, that is, the plurality of reference waterproof material production plans may be P reference waterproof material production plans before a previous reference waterproof material production plan (s waterproof material production plan) of the target waterproof material production plan, and the second production link big data corresponding to the P reference waterproof material production plans is: qs-1, Qs-2, …, Qs-p. Compared with the target waterproof material production plan (s +1), the s waterproof material production plan and the P waterproof material production plans before the s waterproof material production plan are both reference waterproof material production plans of the target waterproof material production plan. In this case, the second production link big data corresponding to the plurality of reference waterproof material production plans before the target waterproof material production plan includes: qs, Qs-1, Qs-2, …, Qs-p, with its corresponding target maintenance fault state sequence { Ws, Ws-1, Ws-2, …, Ws-p }.

The method comprises the steps of obtaining a plurality of dynamic running condition data sequences consisting of s waterproof material production plans before a target waterproof material production plan and P production link big data corresponding to the reference waterproof material production plans before the target waterproof material production plan, then determining a first target dynamic running condition data sequence based on the correlation between the plurality of dynamic running condition data sequences and a target maintenance fault state sequence, wherein in one design thought, the first target dynamic running condition data sequence is a dynamic running condition data sequence consisting of the s waterproof material production plan to the (s-P) waterproof material production plan corresponding production link big data, the first target dynamic running condition data sequence is determined according to correlation parameters between the s waterproof material production plan and the (s-P) waterproof material production plan corresponding target maintenance fault state sequence, and the first target dynamic running condition data sequence is at least two screened second production link big data sequences Combinations of (a) and (b).

And determining a first target dynamic operation condition data sequence based on a dynamic operation condition data sequence consisting of second production link big data and a correlation parameter of a target maintenance fault state sequence, namely screening the first target dynamic operation condition data sequence from the plurality of dynamic operation condition data sequences by using the correlation parameter between the dynamic operation condition data sequence and the target maintenance fault state sequence, so that the information simplification of the second production link big data is realized, and the reference data volume for evaluating the maintenance fault evaluation index is reduced.

And after the first target dynamic operation condition data sequence is obtained, determining the maintenance fault evaluation index of the target waterproof material production plan according to the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the waterproof material production plan which is referred to before the target waterproof material production plan and the first target dynamic operation condition data sequence. The maintenance fault evaluation index of the waterproof material production plan referenced before the target waterproof material production plan can be obtained by adopting the scheme provided by the invention, and the following examples are shown: if the former reference waterproof material production plan of the target waterproof material production plan is the s waterproof material production plan, the maintenance fault evaluation index of the s waterproof material production plan can be obtained according to (s-1) the maintenance fault evaluation index of the waterproof material production plan, the first production link big data of the s waterproof material production plan and the first target dynamic operation state data sequence corresponding to the s waterproof material production plan. In the two related waterproof material production plans, the production link big data of the former waterproof material production plan is used as a reference data set for obtaining the maintenance fault evaluation index of the latter waterproof material production plan, and with continuous traversal processing, the s waterproof material production plan and the production link big data of all the former waterproof material production plans are used as the reference data set of the s waterproof material production plan evaluation result, so that the reference data set for evaluating the maintenance fault evaluation index of the target waterproof material production plan is greatly expanded, and the accuracy of the maintenance fault evaluation index is greatly improved.

Therefore, compared with a mode of fixedly referring to the big data of the production link, the big data of the production link adopted by the invention is richer, so that the accuracy of maintaining the fault evaluation index can be improved; moreover, the first target dynamic operation condition data sequence is obtained based on the correlation parameter of the target maintenance fault state sequence, namely, the first target dynamic operation condition data sequence is obtained by screening the second production link big data based on the correlation parameter, the second production link big data of the maintenance fault evaluation index for evaluating the target waterproof material production plan is simplified, the calculation amount in the evaluation process is facilitated, and the first target dynamic operation condition data sequence strongly related to the maintenance fault evaluation index of the target waterproof material production plan can be obtained by screening the dynamic operation condition data sequence based on the correlation parameter, so that the accuracy and the efficiency of maintenance fault evaluation are improved.

In order to make the person skilled in the art more clearly understand the intelligent management and control scheme for waterproof material production and the technical effects thereof, the following describes in detail specific embodiments with a plurality of possible design ideas.

In a possible design concept, the determining of the first target dynamic operation condition data sequence based on the correlation parameter between the dynamic operation condition data sequence composed of the big data of the second production link and the target maintenance fault state sequence provided in step S130 may be implemented by the following method, including:

step S131, determining a second target dynamic operation state data sequence with the maximum correlation parameter with the target maintenance fault state sequence from the second production link big data.

Step S132, determining a first target dynamic operating condition data sequence based on the second target dynamic operating condition data sequence.

And constructing a plurality of dynamic operation condition data sequences according to a plurality of second production link big data corresponding to the waterproof material production plans before the target waterproof material production plan, wherein each dynamic operation condition data sequence comprises at least one second production link big data, and different dynamic operation condition data sequences can contain the same second production link big data, namely the same dynamic operation condition elements exist in different dynamic operation condition data sequences. A correlation parameter is calculated between each dynamic operating condition data sequence and the target maintenance fault state sequence. For example, the dynamic operating condition data series with the largest correlation parameter is determined as the second target dynamic operating condition data series.

And then determining a first target dynamic operation condition data sequence based on a second target dynamic operation condition data sequence, wherein the first target dynamic operation condition data sequence and the second target dynamic operation condition data sequence both comprise at least two second production link big data. The first target dynamic operation condition data sequence is a sequence formed by a plurality of second production link big data referring to the waterproof material production plan before the target waterproof material production plan, and the number of the specific reference waterproof material production plans is determined by the second target dynamic operation condition data sequence. On the basis that the correlation parameter between the second target dynamic operation condition data sequence and the target maintenance fault state sequence is the largest, the first target dynamic operation condition data sequence is determined based on the second target dynamic operation condition data sequence, so that the correlation parameter between the first target dynamic operation condition data sequence and the evaluation result of the target waterproof material production plan is higher, for example, the first target dynamic operation condition data sequence can be the dynamic operation condition data sequence with the largest correlation parameter with the evaluation result of the target waterproof material production plan, and the accuracy of the maintenance fault evaluation index of the obtained target waterproof material production plan is improved.

It is worth noting that the second target dynamic health data sequence and the first target dynamic health data sequence may contain interleaved second production stage big data, as exemplified by: the second target dynamic operation condition data sequence is { Qs-1, Qs-2, …, Qs-P-1}, and the first target dynamic operation condition data sequence may be { Qs, Qs-1}, that is, the second target dynamic operation condition data sequence may intersect with the production link big data included in the first target dynamic operation condition data sequence, or may have different production link big data, and the sequence data amount of the first target dynamic operation condition data sequence may be different from the sequence data amount of the second target dynamic operation condition data sequence.

In the scheme provided by the embodiment of the invention, the maintenance fault evaluation index of the current waterproof material production plan is evaluated based on a first target dynamic operation state data sequence containing at least two second production link big data, the first target dynamic operation state data sequence is obtained based on a second target dynamic operation state data sequence with the maximum correlation parameter of a target maintenance fault state sequence, the first target dynamic operation state data sequence can be a dynamic operation state data sequence with the maximum correlation parameter of an evaluation result of the target waterproof material production plan, namely, the first target dynamic operation state data sequence can be an optimal sequence of maintenance fault evaluation indexes for accurately evaluating a target waterproof material production plan, so that the accuracy of the maintenance fault evaluation indexes is improved, and the efficiency of obtaining the accurate maintenance fault evaluation indexes is improved.

In one possible design approach, determining a second target dynamic operating condition data sequence with the largest correlation parameter with the target maintenance fault state sequence from the second production link big data includes:

step S1311, determining a plurality of reference dynamic operation state data sequences according to the second production link big data;

step S1312, determining correlation parameters of each reference dynamic operation state data sequence and a target maintenance fault state sequence;

in step S1313, the reference dynamic operation state data series having the largest correlation parameter is determined as the first target dynamic operation state data series.

And forming a dynamic operation state data sequence by the second production link big data, and constructing a plurality of reference dynamic operation state data sequences based on the dynamic operation state data sequence, wherein the reference dynamic operation state data sequence can be obtained by combining the second production link big data in the dynamic operation state data sequence. The second production link big data here may be production link big data of P reference waterproof material production plans corresponding to a previous reference waterproof material production plan of the target waterproof material production plan, such as: the target waterproof material production plan is (s +1) waterproof material production plan, the previous reference waterproof material production plan of the target waterproof material production plan is s waterproof material production plan, the P reference waterproof material production plans corresponding to the previous reference waterproof material production plan of the target waterproof material production plan can be the previous P waterproof material production plans associated with the s waterproof material production plan, namely (s-1), (s-2), …, (s-P), and the dynamic operation condition data sequence consisting of second production link big data corresponding to the s to (s-P) waterproof material production plan is { Qs, Qs-1, Qs-2, …, Qs-P }. The reference dynamic operation condition data sequence constructed based on the dynamic operation condition data sequence can be { Qs, Qs-1, Qs-2}, { Qs-1, Qs-2, Qs-3}, …, { Qs-p-2, Qs-p-1, Qs-p } and the like, and the dimension number of each reference dynamic operation condition data sequence can be different. And calculating the correlation parameter of each reference dynamic operation condition data sequence and the target maintenance fault state sequence, and determining the reference dynamic operation condition data sequence with the maximum correlation parameter as a second target dynamic operation condition data sequence.

In a possible design concept, the determining a plurality of reference dynamic operation status data sequences according to the second production link big data provided in step S1311 may be obtained by:

step S13111, forming a first dynamic operation state data sequence according to the second production link big data;

step S13112, performing data conversion on the first dynamic operation status data sequence to obtain a second dynamic operation status feature distribution, wherein the second dynamic operation status feature distribution is a symmetric feature distribution;

in step 13113, each initial characteristic distribution in the second dynamic behavior characteristic distribution is determined as a reference dynamic behavior data sequence.

In one possible design approach, the determining the first target dynamic operating condition data sequence based on the second target dynamic operating condition data sequence provided in step S132 can be implemented by the following method, including:

step S1321, determining the waterproof material production plan content of the second target dynamic operation state data sequence as the optimal waterproof material production plan content;

step S1322, determining a target reference waterproof material production plan based on the target waterproof material production plan and the content of the optimal waterproof material production plan;

and step S1323, taking a sequence formed by the production link big data of the target reference waterproof material production plan as a first target dynamic operation state data sequence.

And if the first target dynamic operation condition data sequence is the pth and the benchmark dynamic operation condition data sequence, taking the pth as the optimal waterproof material production plan content of the target dynamic operation condition data sequence, namely, the target dynamic operation condition data sequence comprises pth and production link big data.

For example, the plurality of reference dynamic operation condition data sequences may be sorted from near to far in time from the target waterproof material production plan, and if there are p reference dynamic operation condition data sequences, the number of the reference dynamic operation condition data sequence closest to the target waterproof material production plan is set to 1, the number of the reference dynamic operation condition data sequence farthest from the target waterproof material production plan is set to p, and a correlation parameter between the reference dynamic operation condition data sequence and the target maintenance fault state sequence is calculated, and the correlation parameter between each reference dynamic operation condition data sequence and the target maintenance fault state sequence is represented in a sequence form, such as: the correlation parameter sequence is a correlation parameter between the reference dynamic operation state data sequence with the sequence number 1 and the target maintenance fault state sequence, a correlation parameter corresponding to the reference dynamic operation state data sequence with the sequence number p, and so on. The reference dynamic operating condition data series corresponding to the correlation parameter having the largest absolute value of the correlation parameter may be selected and determined as the second target dynamic operating condition data series. And taking the serial number of the reference dynamic operation state data sequence corresponding to the maximum correlation parameter as the optimal waterproof material production plan content.

And determining a target reference waterproof material production plan for evaluating maintenance fault evaluation indexes of the target waterproof material production plan according to the content of the optimal waterproof material production plan, and taking a sequence consisting of production link big data corresponding to the target reference waterproof material production plan as a first target dynamic operation condition data sequence. If the target waterproof material production plan is (s +1) waterproof material production plan and the content of the optimal waterproof material production plan is 4, the target reference waterproof material production plan may be s waterproof material production plan, (s-1) waterproof material production plan, (s-2) waterproof material production plan, (s-3) waterproof material production plan, and the first target dynamic operation condition data sequence is { Qs, Qs-1, Qs-2, Qs-3 }.

When the first target dynamic operation condition data sequence is determined, firstly, the content of the optimal waterproof material production plan is determined, then the first target dynamic operation condition data sequence corresponding to the target waterproof material production plan is determined based on the content of the optimal waterproof material production plan, the first target dynamic operation condition data sequence corresponding to each target waterproof material production plan can be determined, and the assessment accuracy of the maintenance fault assessment index of the target waterproof material production plan is improved.

The implementation process for determining the target dynamic operation state data sequence provided by one possible design idea of the invention is as follows: first, a second target dynamic operation condition data sequence with the maximum correlation parameter with the target maintenance fault state sequence is determined from the second production link big data, and the step can be performed through the schemes provided in the steps S1311 to S1313, wherein the determination of the plurality of reference dynamic operation condition data sequences according to the sequence formed by the second production link big data can be performed through the schemes provided in the steps S13111 to S13113; then, the first target dynamic operating condition data series is determined based on the second target dynamic operating condition data series, which may be performed by the schemes provided in step S1321 to step S1323. According to the scheme provided by the embodiment, the first target dynamic operation condition data sequence can be rapidly determined from a large amount of second production link big data, so that the maintenance fault evaluation index can be more accurately evaluated based on the first target dynamic operation condition data sequence.

To further clarify the related managed partition evaluation scheme provided by the present invention, it may be explained with reference to specific examples. Suppose that the input Ws of the s waterproof material production plan includes the input (Ws-1) of the last waterproof material production plan (s-1) thereof, the second production link big data { Qs-1, Qs-2, …, Qs-p } of the plurality of reference waterproof material production plans { s-1, s-2, …, s-p }, and the first production link big data Qs of the s waterproof material production plan. The output of the s waterproofing material production plan is related to the input Ws of the s waterproofing material production plan. In the embodiment of the invention, the input Ws of the s waterproof material production plan is used as the maintenance fault evaluation index of the s waterproof material production plan, and the Qs output based on the maintenance fault evaluation index is output as the data after further processing.

In the related technology, the model input characteristic of the s waterproof material production plan only adopts the big data of the production link including the current target waterproof material production plan and the previous stage thereof, namely when the s waterproof material production plan is the target waterproof material production plan, only the big data of the production link of the (s-1) waterproof material production plan is used as the model input characteristic of the target waterproof material production plan. Moreover, the second production link big data can be obtained by using the scheme for screening the target production link big data, so that the accuracy of an evaluation result, namely the maintenance fault evaluation index of the target waterproof material production plan, is further improved, and the efficiency of obtaining an accurate evaluation result can be improved.

In addition, the related management and control partition evaluation method provided by the possible design idea can be carried out in a model mode, so that the efficiency and the accuracy of obtaining an evaluation result are further improved.

For example, the step of determining the maintenance failure evaluation index of the target waterproof material production plan according to the first production link big data of the target waterproof material production plan, the maintenance failure evaluation index of the previous reference waterproof material production plan of the target waterproof material production plan, and the first target dynamic operation condition data sequence, which are provided in step S140, may be performed by:

using the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the waterproof material production plan which is referred to in the front of the target waterproof material production plan and the first target dynamic operation state data sequence as the input of a maintenance fault evaluation index prediction model to obtain the maintenance fault evaluation index of the target waterproof material production plan;

in one possible design idea, the model configuration process for maintaining the fault assessment indicator prediction model is as follows:

b1, acquiring a reference data set, wherein the reference data set comprises a plurality of reference dynamic operation state data sequences corresponding to the reference waterproof material production plan and corresponding maintenance fault states; and the reference dynamic operation state data sequence corresponding to each reference waterproof material production plan comprises a plurality of reference production link big data.

And B2, training the model optimization of the initial AI model by using the reference data set until the model evaluation index corresponding to the initial AI model reaches the model convergence condition, taking the initial AI model corresponding to the model evaluation index meeting the model convergence condition as a maintenance fault evaluation index prediction model, wherein the value of the model evaluation index represents loss information between the predicted maintenance fault state and the maintenance fault state output by the maintenance fault evaluation index prediction model.

In the embodiment of the invention, each reference data set of the maintenance fault evaluation index prediction model comprises a plurality of reference dynamic operation state data sequences corresponding to reference waterproof material production plans and corresponding maintenance fault states, each group of reference data sets comprises one reference dynamic operation state data sequence corresponding to a reference waterproof material production plan and a corresponding maintenance fault state, one reference dynamic operation state data sequence corresponding to a reference waterproof material production plan comprises a plurality of reference production link big data, and the reference production link big data is reference production link big data.

And if the value of the model evaluation index does not meet the model convergence requirement, the value of the model evaluation index is used for adjusting the network weight until the initial AI model converges, and the initial AI model at the time of convergence is a maintenance fault evaluation index prediction model.

Of course, for the obtained reference data set, a part of test data used for maintaining the fault assessment index prediction model may be reserved, for example, the reference data set may be randomly divided into reference sample data (ratio a) and reference test data (ratio 1-a) according to a preset ratio. And when the value of the model evaluation index corresponding to the reference test data meets the model convergence condition of the maintenance fault evaluation index prediction model, ending the training. The model evaluation index can be represented as an index such as accuracy, when the model evaluation index is lower than a preset model evaluation index, the initial AI model can be judged to reach a model convergence condition, and the converged initial AI model is a maintenance fault evaluation index prediction model. The training of the maintenance fault evaluation index prediction model in the embodiment of the invention is carried out based on a plurality of reference dynamic operation state data sequences corresponding to the reference waterproof material production plan and corresponding maintenance fault states, wherein each reference dynamic operation state data sequence comprises a plurality of second production link big data. And model configuration optimization is carried out based on the second production link big data, so that the trained maintenance fault assessment index prediction model takes the influence factors of the second production link big data into consideration, and compared with the mode of carrying out model configuration optimization by adopting the second production link big data, the assessment accuracy of the maintenance fault assessment index prediction model obtained by utilizing the second production link big data is improved.

According to the related management and control partition evaluation scheme provided by the invention, the maintenance fault evaluation index of the target waterproof material production plan is evaluated by utilizing the pre-trained maintenance fault evaluation index prediction model, so that the maintenance fault evaluation index of the target waterproof material production plan can be rapidly determined. For example, it may be used to perform the steps of the aforementioned steps S110 to S140.

For example, the reference data set of the maintenance fault evaluation index prediction model includes reference dynamic operation condition data sequences corresponding to a plurality of reference waterproof material production plans and corresponding maintenance fault states, and the reference dynamic operation condition data sequence corresponding to each reference waterproof material production plan may include a sequence formed by reference production link big data corresponding to the reference waterproof material production plan and a first training target dynamic operation condition data sequence corresponding to the reference waterproof material production plan. If one reference waterproof material production plan in the reference data set is the s waterproof material production plan, the reference dynamic operation condition data sequence corresponding to the s waterproof material production plan comprises reference production link big data corresponding to the s waterproof material production plan and a first training target dynamic operation condition data sequence corresponding to the s waterproof material production plan, and the first training target dynamic operation condition data sequence corresponding to the s waterproof material production plan can be obtained based on the optimal waterproof material production plan content obtained by the method. Examples are as follows: if the content of the optimal waterproof material production plan is p, the reference dynamic operation condition data sequence corresponding to the s waterproof material production plan comprises first production link big data Qs corresponding to the s waterproof material production plan and a first target dynamic operation condition data sequence { Qs-1, …, Qs-p } corresponding to the s waterproof material production plan, namely the reference dynamic operation condition data sequence corresponding to the s waterproof material production plan is { Qs, Qs-1, …, Qs-p }.

In the solution provided in this embodiment, the reference dynamic operation state data sequence is a sequence composed of reference production link big data corresponding to a reference waterproof material production plan and a first training target dynamic operation state data sequence corresponding to the reference waterproof material production plan. That is, the model input features in each set of reference data sets are each composed of a plurality of second production link big data having the greatest correlation with the maintenance fault state. The scheme provided by the embodiment is that screening is performed on the basis of the plurality of second dynamic operation condition data sequences, and the reference dynamic operation condition data sequences formed by the second production link big data with high correlation parameters with the maintenance fault abnormal state result are used as the model input characteristics of the model to perform model configuration optimization, so that the accuracy of maintaining the fault evaluation index prediction model can be further improved, and the efficiency of obtaining the maintenance fault evaluation index prediction model is facilitated.

For example, in the process of configuring the model for maintaining the fault assessment index prediction model, the method further includes:

and C1, performing data splitting on the reference production link big data in the reference data set to obtain first reference production link big data and second reference production link big data.

C2, respectively encoding data for the first reference production link big data and the second reference production link big data.

And C3, using the first reference production link big data and the second reference production link big data after data encoding and the corresponding maintenance fault states as model input features of the initial AI model to perform model configuration optimization.

And dividing the reference production link big data in the reference data set according to the data types, wherein the reference production link big data can be second production link big data, and corresponding data coding is carried out on the reference production link big data of different data types, so that the efficiency of the production link big data is improved, and meanwhile, the characteristic loss can be reduced to the maximum extent.

And then, model configuration optimization is carried out by utilizing the big data and the dense reference data set of the first reference production link after data coding, so that the data processing amount of the model is favorably reduced, and the training efficiency of the model is favorably improved.

In one possible design idea, the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the waterproof material production plan that is referred to before the target waterproof material production plan, and the first target dynamic operation state data sequence are used as the input of the maintenance fault evaluation index prediction model to obtain the maintenance fault evaluation index of the target waterproof material production plan, and the method can be performed in the following manner, and includes:

d1, performing data splitting on the second production link big data in the first target dynamic operation state data sequence and the first production link big data of the target waterproof material production plan to obtain first production link big data and second production link big data;

d2, performing feature coding on sparse feature data to obtain sparse feature components corresponding to the big data of the first production link;

and D3, inputting the sparse characteristic component, the dense characteristic component and the maintenance fault evaluation index of the waterproof material production plan which is referred to in front of the target waterproof material production plan into a maintenance fault evaluation index prediction model to obtain the maintenance fault evaluation index of the target waterproof material production plan.

Dividing the production link big data by a first production link big data corresponding to a target waterproof material production plan (s +1) and a dynamic operation condition data sequence { Qs +1, Qs, …, Qs-p +1} consisting of the first target dynamic operation condition data sequence, dividing the production link big data into the first production link big data and a second production link big data, carrying out feature coding on the first production link big data, carrying out feature coding by using a pre-trained deep AI model, and obtaining a sparse feature component corresponding to the first production link big data in the dynamic operation condition data sequence corresponding to the target waterproof material production plan. And finally, inputting the sparse characteristic component and dense characteristics in a dynamic operation state data sequence corresponding to the target waterproof material production plan into a trained maintenance fault evaluation index prediction model to obtain a maintenance fault evaluation index of the target waterproof material production plan, wherein the output is 1 when the maintenance fault evaluation index is larger than the target evaluation index, and the output is 0 when the maintenance fault evaluation index is not larger than the target evaluation index.

In the related managed partition evaluation scheme provided in the foregoing embodiment, for example, the first production link big data and/or the second production link big data may include: and representing at least one production link big data of production link time control data, production link energy consumption control data and production link early warning control data.

Correspondingly, one possible design idea of the invention also provides a related management and control partition evaluation method, which comprises the following steps:

e1, acquiring a reference data set and an initial AI model; the reference data set comprises a plurality of reference dynamic operation state data sequences corresponding to the reference waterproof material production plans and corresponding maintenance fault states, and the reference dynamic operation state data sequence corresponding to each reference waterproof material production plan comprises a plurality of reference production link big data;

e2, inputting the reference dynamic operation state data sequence corresponding to each reference waterproof material production plan into the initial AI model to obtain the predicted maintenance fault state corresponding to each reference characteristic waterproof material production plan, and determining the value of the model evaluation index based on the predicted maintenance fault state and the maintenance fault state corresponding to the reference waterproof material production plan;

e3, training the initial AI model based on the values of the model evaluation indexes until the model evaluation indexes of the initial AI model meet the model convergence condition, and evaluating the maintenance fault evaluation indexes by taking the initial AI model when the model evaluation indexes meet the model convergence condition as a maintenance fault evaluation index prediction model.

In the embodiment of the invention, each reference data set of the maintenance fault evaluation index prediction model comprises a plurality of reference dynamic operation state data sequences corresponding to reference waterproof material production plans and corresponding maintenance fault states, each group of reference data sets comprises one reference dynamic operation state data sequence corresponding to a reference waterproof material production plan and a corresponding maintenance fault state, one reference dynamic operation state data sequence corresponding to a reference waterproof material production plan comprises a plurality of reference production link big data, and the reference production link big data can be second production link big data.

The training of the maintenance fault evaluation index prediction model in the embodiment of the invention is carried out based on a plurality of reference dynamic operation state data sequences corresponding to the reference waterproof material production plan and corresponding maintenance fault states, wherein each reference dynamic operation state data sequence comprises a plurality of second production link big data. And model configuration optimization is carried out based on the second production link big data, so that the trained maintenance fault assessment index prediction model takes the influence factors of the second production link big data into consideration, and compared with the mode of carrying out model configuration optimization by adopting the second production link big data, the assessment accuracy of the maintenance fault assessment index prediction model obtained by utilizing the second production link big data is improved.

For example, the reference dynamic operation condition data sequence corresponding to each reference waterproof material production plan includes reference production link big data corresponding to the reference waterproof material production plan and a first training target dynamic operation condition data sequence corresponding to the reference waterproof material production plan.

In this embodiment, the reference data set of the model includes reference dynamic operation state data sequences corresponding to a plurality of reference waterproof material production plans and corresponding maintenance fault states, and the reference dynamic operation state data sequence corresponding to each reference waterproof material production plan may include a sequence composed of reference production link big data corresponding to the reference waterproof material production plan and a first training target dynamic operation state data sequence corresponding to the reference waterproof material production plan. Such as one of the reference data sets referring to the waterproof material production plan as s waterproof material production plan, the reference dynamic operation condition data sequence corresponding to the s waterproof material production plan includes reference production link big data corresponding to the s waterproof material production plan and a first training target dynamic operation condition data sequence corresponding to the s waterproof material production plan, the first training target dynamic operation condition data sequence corresponding to the s waterproof material production plan may be a first target dynamic operation condition data sequence obtained based on the foregoing method (the first target dynamic operation condition data sequence corresponding to the s waterproof material production plan is determined based on the content of the optimal waterproof material production plan), if the first target dynamic operation condition data sequence is used for model configuration optimization, the first target dynamic operating condition data sequence is taken as a first training target dynamic operating condition data sequence.

For example: assuming that the content of the optimal waterproof material production plan is p, the reference dynamic operation condition data sequence corresponding to the s waterproof material production plan comprises reference production link big data Qs corresponding to the s waterproof material production plan and a first training target dynamic operation condition data sequence { Qs-1, …, Qs-p } corresponding to the s waterproof material production plan, namely the reference dynamic operation condition data sequence corresponding to the s waterproof material production plan is { Qs, Qs-1, …, Qs-p }.

In the solution provided in this embodiment, the reference dynamic operation state data sequence is a sequence composed of production link big data corresponding to the reference waterproof material production plan and a first training target dynamic operation state data sequence corresponding to the reference waterproof material production plan. That is, the model input features in each set of reference data sets are each composed of a plurality of second production link big data having the greatest correlation with the maintenance fault state. The scheme provided by the embodiment is that screening is performed on the basis of a plurality of reference production link big data, a reference dynamic operation state data sequence formed by a plurality of second production link big data with high correlation parameters with maintenance fault abnormal state results is used as a model input feature of the model to perform model configuration optimization, the accuracy of maintaining the fault assessment index prediction model can be further improved, and meanwhile, the efficiency of obtaining the maintenance fault assessment index prediction model is favorably improved.

In a possible design idea, an embodiment of the present invention provides an intelligent management and control method for waterproof material production based on big data statistics, which may include the following steps.

Step S210, determining whether the maintenance fault evaluation index of the relevant control partition of the target waterproof material production plan is greater than a preset maintenance fault evaluation index.

Step S220, when the maintenance fault evaluation index of the related control partition of the target waterproof material production plan is larger than the preset maintenance fault evaluation index, performing intelligent management and control on the related control partition of the target waterproof material production plan.

The specific implementation manner of performing intelligent management and control on the relevant control partition of the target waterproof material production plan in step S220 may include the following steps.

Step S221, acquiring fault maintenance behavior information of a current fault maintenance node of a related control partition aiming at a target waterproof material production plan; the method comprises the steps that fault maintenance control instruction information of each same fault maintenance behavior of fault maintenance behavior information of each fault maintenance node corresponds to a group of intelligent management and control strategies, and each group of intelligent management and control strategies comprises a first intelligent management and control strategy which is preset according to fault maintenance switching cost information of fault maintenance behavior information of related management and control partitions of a target waterproof material production plan in preset number; the fault maintenance switching cost information of the fault maintenance behavior information of the related control subarea of the target waterproof material production plan is real-time fault maintenance switching cost information of behavior updating data with fault maintenance behavior node information switching in the related control subarea of the target waterproof material production plan;

step S222, aiming at each current fault maintenance control instruction information in the fault maintenance behavior information of the current fault maintenance node, matching the control instruction content characteristics of the current fault maintenance control instruction information with a group of intelligent management and control strategies corresponding to the current fault maintenance control instruction information;

step S223, if the control instruction content characteristics of the current fault maintenance control instruction information are successfully matched with any first intelligent management control strategy in a group of intelligent management control strategies corresponding to the current fault maintenance control instruction information, updating the control instruction content characteristics of the successfully matched first intelligent management control strategy according to the control instruction content characteristics of the current fault maintenance control instruction information, and determining the current fault maintenance control instruction information as first starting fault maintenance control instruction information;

step S224, if the matching of the content characteristics of the control instruction of the current fault maintenance control instruction information and all the first intelligent management control strategies in a group of intelligent management control strategies corresponding to the current fault maintenance control instruction information fails, selecting one first intelligent management control strategy from the group of intelligent management control strategies corresponding to the current fault maintenance control instruction information, modifying the content characteristics of the control instruction of the selected first intelligent management control strategy, and determining first candidate fault maintenance control instruction information according to the current fault maintenance control instruction information;

step S225, determining whether the fault maintenance behavior information of the current fault maintenance node contains first candidate fault maintenance control instruction information;

step S226, determining whether the second fault maintenance enabling control instruction information exists in the fault maintenance behavior information of the current fault maintenance node according to whether the fault maintenance behavior information of the current fault maintenance node includes the first candidate fault maintenance control instruction information.

And step S227, performing intelligent management and control on the related management and control partition of the target waterproof material production plan according to the obtained first starting fault maintenance control instruction information and the second starting fault maintenance control instruction information.

In one possible design concept, the embodiment of the present invention may further include the following steps.

Step S310, judging whether the maintenance fault evaluation index of the related control subarea of the target waterproof material production plan is larger than a preset maintenance fault evaluation index.

Step S320, when the maintenance fault evaluation index of the relevant control partition of the target waterproof material production plan is not greater than the preset maintenance fault evaluation index, updating the management control policy corresponding to the relevant control partition of the target waterproof material production plan.

In one possible design concept, step S320 can be implemented as follows.

Step S321, obtaining a feedback control model data set collected by a plurality of production intelligent monitoring devices.

Step S322, generating management control update data of the target feedback control model node according to the feedback control model data set.

Step S323, updating the management control policy corresponding to the relevant control partition based on the management control update data of the target feedback control model node.

Fig. 3 is a schematic functional module diagram of an intelligent management and control device 300 for waterproof material production based on big data statistics according to an embodiment of the present invention, and the functions of the functional modules of the intelligent management and control device 300 for waterproof material production based on big data statistics are described in detail below.

The first obtaining module 310 is configured to obtain first production link big data of each production intelligent monitoring device of a relevant control partition of the target waterproof material production plan and a maintenance fault evaluation index of a previous reference waterproof material production plan of the target waterproof material production plan.

The second obtaining module 320 is configured to obtain second production link big data and a target maintenance fault state sequence corresponding to a plurality of reference waterproof material production plans before the target waterproof material production plan. The first production link big data and/or the second production link big data comprise: and characterizing at least one production link big data of production link temperature control data, production link time control data, production link energy consumption control data and production link early warning control data.

The first determining module 330 is configured to determine a first target dynamic operation status data sequence based on a correlation parameter between a dynamic operation status data sequence composed of second production link big data and a target maintenance fault state sequence, where the first target dynamic operation status data sequence includes at least two second production link big data referring to a waterproof material production plan.

The second determining module 340 is configured to determine a maintenance fault evaluation index of the target waterproof material production plan according to the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the waterproof material production plan that is referred to before the target waterproof material production plan, and the first target dynamic operation status data sequence.

Fig. 4 illustrates a hardware structural diagram of an intelligent management and management cloud service platform 100 for implementing the above-mentioned waterproof material production intelligent management and management method based on big data statistics, where as shown in fig. 4, the intelligent management and management cloud service platform 100 may include a processor 110, a machine-readable storage medium 120, a bus 130, and a transceiver 140.

In a specific implementation process, at least one processor 110 executes machine executable instructions stored in the machine readable storage medium 120, so that the processor 110 may execute the waterproof material production intelligent management and control method based on big data statistics according to the above method embodiment, the processor 110, the machine readable storage medium 120, and the transceiver 140 are connected through the bus 130, and the processor 110 may be configured to control the transceiving action of the transceiver 140, so as to perform data transceiving with the production intelligent monitoring apparatus 200.

For a specific implementation process of the processor 110, reference may be made to the above-mentioned method embodiments executed by the intelligent management and control cloud service platform 100, which implement principles and technical effects are similar, and details of this embodiment are not described herein again.

In addition, the embodiment of the invention also provides a readable storage medium, wherein the readable storage medium is preset with machine executable instructions, and when a processor executes the machine executable instructions, the waterproof material production intelligent management and control method based on big data statistics is realized.

Finally, it should be understood that the examples in this specification are only intended to illustrate the principles of the examples in this specification. Other variations are also possible within the scope of this description. Accordingly, by way of example, and not limitation, alternative configurations of the embodiments of the specification can be seen as matching the teachings of the specification. Accordingly, the embodiments of the present description are not limited to only those embodiments explicitly described and depicted herein.

Claims

1. The intelligent management and control method for waterproof material production based on big data statistics is applied to an intelligent management and control cloud service platform, wherein the intelligent management and control cloud service platform is in communication connection with a plurality of intelligent production monitoring devices, and the method comprises the following steps:

2. The intelligent management and control method for waterproof material production based on big data statistics as claimed in claim 1, wherein the determining a first target dynamic operation condition data sequence based on the correlation parameters of the dynamic operation condition data sequence composed of the second production link big data and the target maintenance fault state sequence comprises:

determining a second target dynamic operation condition data sequence with the maximum correlation parameter with the target maintenance fault state sequence based on the second production link big data;

determining the first target dynamic operating condition data sequence based on the second target dynamic operating condition data sequence;

wherein the determining a second target dynamic operating condition data sequence with the largest correlation parameter with the target maintenance fault state sequence based on the second production link big data comprises:

determining a plurality of reference dynamic operation condition data sequences according to a plurality of second production link big data, determining correlation parameters of each reference dynamic operation condition data sequence and the target maintenance fault state sequence, and determining the reference dynamic operation condition data sequence with the maximum correlation parameter as the second target dynamic operation condition data sequence;

said determining said first target dynamic operating condition data sequence based on said second target dynamic operating condition data sequence comprises:

and determining the waterproof material production plan content of the second target dynamic operation condition data sequence as the optimal waterproof material production plan content, determining a target reference waterproof material production plan based on the target waterproof material production plan and the optimal waterproof material production plan content, and taking a sequence formed by production link big data of the target reference waterproof material production plan as the first target dynamic operation condition data sequence.

3. The intelligent management and control method for waterproof material production based on big data statistics as claimed in claim 2, wherein the determining a plurality of reference dynamic operation condition data sequences according to the plurality of second production link big data comprises:

forming a first dynamic operation state data sequence according to the large data of the second production links;

performing data conversion on the first dynamic operation condition data sequence to obtain a second dynamic operation condition characteristic distribution;

determining each initial characteristic distribution in the second dynamic operating condition characteristic distribution as a reference dynamic operating condition data sequence.

4. The intelligent management and control method for waterproof material production based on big data statistics as claimed in claim 1, wherein the determining the maintenance fault evaluation index of the target waterproof material production plan according to the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the previous reference waterproof material production plan of the target waterproof material production plan, and the first target dynamic operation status data sequence comprises:

the model configuration process for maintaining the fault assessment index prediction model is as follows:

acquiring a reference data set, wherein the reference data set comprises reference dynamic operation condition data sequences corresponding to a plurality of reference waterproof material production plans and corresponding maintenance fault states, and the reference dynamic operation condition data sequences corresponding to the plurality of reference waterproof material production plans comprise a plurality of reference production link big data;

and performing training model optimization on the initial AI model by using the reference data set until the model evaluation index corresponding to the initial AI model reaches a model convergence condition, taking the initial AI model corresponding to the model evaluation index meeting the model convergence condition as a maintenance fault evaluation index prediction model, wherein the value of the model evaluation index represents loss information between a predicted maintenance fault state and a maintenance fault state output by the maintenance fault evaluation index prediction model.

5. The intelligent management and control method for waterproof material production based on big data statistics, according to claim 4, before training model optimization of the initial AI model by using the reference data set, further comprising:

performing data splitting on the reference production link big data in the reference data set to obtain first reference production link big data and second reference production link big data, wherein the first reference production link big data and the second reference production link big data are respectively sparse reference production link big data and dense reference production link big data;

respectively carrying out data encoding on the first reference production link big data and the second reference production link big data;

and using the first reference production link big data and the second reference production link big data after data encoding and the maintenance fault states corresponding to the first reference production link big data and the second reference production link big data as the model input characteristics of the initial AI model.

6. The intelligent management and control method for waterproof material production based on big data statistics as claimed in claim 4, wherein the obtaining of the maintenance fault evaluation index of the target waterproof material production plan by taking the first production link big data of the target waterproof material production plan, the maintenance fault evaluation index of the previous reference waterproof material production plan of the target waterproof material production plan, and the first target dynamic operation condition data sequence as the input of the maintenance fault evaluation index prediction model comprises:

performing data splitting on second production link big data in the first target dynamic operation condition data sequence and first production link big data of a target waterproof material production plan to obtain first production link big data and second production link big data;

performing feature coding on the first production link big data to obtain a sparse feature component corresponding to the first production link big data;

and inputting the sparse characteristic component, the second production link big data and the maintenance fault evaluation index of the waterproof material production plan which is the last reference of the target waterproof material production plan into the maintenance fault evaluation index prediction model to obtain the maintenance fault evaluation index of the target waterproof material production plan.

7. The intelligent management and control method for waterproof material production based on big data statistics as claimed in any one of claims 1-6, wherein the method further comprises:

judging whether the maintenance fault evaluation index of the related control partition of the target waterproof material production plan is larger than a preset maintenance fault evaluation index or not, and when the maintenance fault evaluation index of the related control partition of the target waterproof material production plan is larger than the preset maintenance fault evaluation index, performing intelligent management and control on the related control partition of the target waterproof material production plan;

wherein the step of intelligently managing and controlling the relevant control partition of the target waterproof material production plan comprises:

obtaining fault maintenance behavior information of a current fault maintenance node of a related control partition of the target waterproof material production plan based on a maintenance fault evaluation index of the related control partition of the target waterproof material production plan; the method comprises the steps that fault maintenance control instruction information of each same fault maintenance behavior of fault maintenance behavior information of each fault maintenance node corresponds to a group of intelligent management and control strategies, and each group of intelligent management and control strategies comprises a first intelligent management and control strategy which is preset according to fault maintenance switching cost information of fault maintenance behavior information of related management and control partitions of a target waterproof material production plan in preset number; the fault maintenance switching cost information of the fault maintenance behavior information of the control subarea related to the target waterproof material production plan is real-time fault maintenance switching cost information of behavior updating data with fault maintenance behavior node information switching in the control subarea related to the target waterproof material production plan;

for each current fault maintenance control instruction information in the fault maintenance behavior information of the current fault maintenance node, matching the control instruction content characteristics of the current fault maintenance control instruction information with a group of intelligent management and control strategies corresponding to the current fault maintenance control instruction information;

if the control instruction content characteristics of the current fault maintenance control instruction information are successfully matched with any first intelligent management and control strategy in a group of intelligent management and control strategies corresponding to the current fault maintenance control instruction information, updating the control instruction content characteristics of the successfully matched first intelligent management and control strategy according to the control instruction content characteristics of the current fault maintenance control instruction information, and determining the current fault maintenance control instruction information as first starting fault maintenance control instruction information;

if the matching of the control instruction content characteristics of the current fault maintenance control instruction information and all first intelligent management and control strategies in a group of intelligent management and control strategies corresponding to the current fault maintenance control instruction information fails, selecting one first intelligent management and control strategy from the group of intelligent management and control strategies corresponding to the current fault maintenance control instruction information, modifying the control instruction content characteristics of the selected first intelligent management and control strategy, and determining first candidate fault maintenance control instruction information according to the current fault maintenance control instruction information;

determining whether the fault maintenance behavior information of the current fault maintenance node contains first candidate fault maintenance control instruction information;

determining whether second fault maintenance starting control instruction information exists in the fault maintenance behavior information of the current fault maintenance node according to whether the fault maintenance behavior information of the current fault maintenance node contains first candidate fault maintenance control instruction information;

and performing intelligent management and control on the related management and control partition of the target waterproof material production plan according to the obtained first starting fault maintenance control instruction information and the second starting fault maintenance control instruction information.

8. The intelligent management and control method for waterproof material production based on big data statistics as claimed in any one of claims 1-6, wherein the method further comprises:

and judging whether the maintenance fault evaluation index of the related control subarea of the target waterproof material production plan is larger than a preset maintenance fault evaluation index or not, and updating a management control strategy corresponding to the related control subarea of the target waterproof material production plan when the maintenance fault evaluation index of the related control subarea of the target waterproof material production plan is not larger than the preset maintenance fault evaluation index.

9. The intelligent management and control method for waterproof material production based on big data statistics as claimed in claim 8, wherein the step of updating the management and control policy corresponding to the relevant control partition of the target waterproof material production plan comprises:

acquiring a feedback control model data set collected by a plurality of production intelligent monitoring devices in a production monitoring network associated with the relevant control subarea, wherein the feedback control model data set comprises at least one feedback control model data and feedback control path information of the feedback control model data;

generating management control update data of target feedback control model nodes according to the feedback control model data set;

and updating the management control strategy corresponding to the relevant control subarea based on the management control updating data of the target feedback control model node.

10. The waterproof material production intelligent management and control system based on big data statistics is characterized by comprising an intelligent management and control cloud service platform and a plurality of production intelligent monitoring devices in communication connection with the intelligent management and control cloud service platform;

the intelligent management and control cloud service platform is used for: