CN117162263B - Method and system for optimizing concrete production process - Google Patents
Method and system for optimizing concrete production process Download PDFInfo
- Publication number
- CN117162263B CN117162263B CN202311446632.6A CN202311446632A CN117162263B CN 117162263 B CN117162263 B CN 117162263B CN 202311446632 A CN202311446632 A CN 202311446632A CN 117162263 B CN117162263 B CN 117162263B
- Authority
- CN
- China
- Prior art keywords
- stirring
- control
- stirring control
- performance
- concrete
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 239000004567 concrete Substances 0.000 title claims abstract description 192
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 86
- 238000000034 method Methods 0.000 title claims abstract description 74
- 238000003756 stirring Methods 0.000 claims abstract description 455
- 238000012795 verification Methods 0.000 claims abstract description 212
- 238000002156 mixing Methods 0.000 claims abstract description 115
- 238000005457 optimization Methods 0.000 claims abstract description 19
- 238000009412 basement excavation Methods 0.000 claims abstract description 3
- 238000013019 agitation Methods 0.000 claims description 69
- 239000000203 mixture Substances 0.000 claims description 43
- 238000012216 screening Methods 0.000 claims description 14
- 238000007418 data mining Methods 0.000 claims description 12
- 238000012549 training Methods 0.000 claims description 12
- 238000013528 artificial neural network Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 230000010354 integration Effects 0.000 claims description 5
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010200 validation analysis Methods 0.000 claims description 3
- 230000009897 systematic effect Effects 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 19
- 239000002994 raw material Substances 0.000 description 12
- 238000003062 neural network model Methods 0.000 description 7
- 239000004568 cement Substances 0.000 description 6
- 239000004576 sand Substances 0.000 description 6
- 230000000694 effects Effects 0.000 description 5
- 238000007580 dry-mixing Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000011217 control strategy Methods 0.000 description 3
- 239000011372 high-strength concrete Substances 0.000 description 3
- 239000004575 stone Substances 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 239000007788 liquid Substances 0.000 description 2
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000013433 optimization analysis Methods 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 239000013598 vector Substances 0.000 description 1
Landscapes
- Preparation Of Clay, And Manufacture Of Mixtures Containing Clay Or Cement (AREA)
Abstract
The invention provides a method and a system for optimizing a concrete production process, which relate to the technical field of concrete production process optimization and comprise the following steps: connecting a concrete production management end, obtaining the mixing proportion characteristic of target concrete, obtaining N working performance constraints corresponding to N working performance indexes, carrying out stirring control stage division, obtaining G stirring control stages, carrying out stirring control molecule excavation, obtaining stirring control molecule space, constructing a stirring control performance verification chain, carrying out stirring control optimizing, obtaining a target stirring control decision, encrypting and transmitting to the concrete production management end, and stirring the target concrete. The invention solves the problems that the traditional concrete production process lacks a systematic method for stirring control, and the traditional concrete production process usually depends on an empirical judgment or trial-and-error method for adjustment in order to achieve the target working performance requirement, so that the efficiency is low and the quality is unstable.
Description
Technical Field
The invention relates to the technical field of concrete production process optimization, in particular to a method and a system for optimizing a concrete production process.
Background
In conventional concrete production, the stirring control is usually performed based on experience and experiment, and a definite systematic method is not available to determine the appropriate stirring parameters such as stirring time, stirring speed and the like, and an operator often adjusts according to experience, which easily causes inconsistency and quality fluctuation in the production process. In addition, the traditional concrete production process also lacks a structuring method to meet the target working performance requirement, and the required characteristics of concrete strength, fluidity, durability and the like can be met through repeated test and adjustment in the production process, so that the error testing method is obviously low in efficiency and is easy to cause unstable concrete quality.
Therefore, a new optimization method of concrete production process is needed, a more systematic and scientific concrete production flow is established, and the controllability, efficiency and quality stability of the concrete production process are improved.
Disclosure of Invention
The application provides a method and a system for optimizing a concrete production process, which aim to solve the technical problems that the traditional concrete production process lacks a systematic method for stirring control, and the method usually depends on an empirical judgment or trial-and-error method for adjustment to achieve target working performance, so that the efficiency is low and the quality is unstable.
In view of the above problems, the present application provides a method and a system for optimizing a concrete production process.
In a first aspect of the disclosure, there is provided a method for optimizing a production process of concrete, the method comprising: connecting a concrete production management end to obtain the mixing proportion characteristic of target concrete; the concrete production management end is interacted to obtain N working performance constraints corresponding to N working performance indexes of the target concrete, wherein N is a positive integer greater than 1; dividing the stirring control stages of the target concrete based on the mixing proportion characteristics and the N working performance constraints to obtain G stirring control stages, wherein G is a positive integer greater than 1; digging stirring control molecules based on the mixing proportion characteristics and the G stirring control stages to obtain a stirring control molecule space; constructing a stirring control performance verification chain based on the mixing proportion characteristics and the N working performance constraints; based on the mixing proportion characteristic and the stirring control performance verification chain, executing stirring control optimizing of the target concrete according to the stirring control molecular space to obtain a target stirring control decision; and encrypting and transmitting the target stirring control decision to the concrete production management end, and stirring the target concrete according to the target stirring control decision.
In another aspect of the present disclosure, there is provided a system for optimizing a production process of concrete, the system being used for the above method, the system comprising: the characteristic acquisition module is used for connecting a concrete production management end to obtain the mixing proportion characteristic of target concrete; the performance constraint acquisition module is used for interacting the concrete production management end to obtain N working performance constraints corresponding to N working performance indexes of the target concrete, wherein N is a positive integer greater than 1; the control phase division module is used for carrying out stirring control phase division on the target concrete based on the mixing proportion characteristics and the N working performance constraints to obtain G stirring control phases, wherein G is a positive integer greater than 1; the control molecule excavating module is used for carrying out stirring control molecule excavating based on the mixing proportion characteristics and the G stirring control stages to obtain a stirring control molecule space; the verification chain construction module is used for constructing a stirring control performance verification chain based on the mixing proportion characteristics and the N working performance constraints; the stirring control optimizing module is used for executing stirring control optimizing of the target concrete according to the stirring control molecular space based on the mixing ratio characteristics and the stirring control performance verification chain to obtain a target stirring control decision; and the concrete stirring module is used for encrypting and transmitting the target stirring control decision to the concrete production management end, and stirring the target concrete according to the target stirring control decision.
One or more technical solutions provided in the present application have at least the following technical effects or advantages:
according to the mixing proportion characteristics of target concrete and the constraint of working performance, dividing the concrete production process into a plurality of stirring control stages, so that the stirring process of the concrete is better controlled; based on the mixing proportion characteristics and the stirring control stage, an adjustable stirring parameter is obtained by exploring a stirring control molecular space, and the controllability and the efficiency of the stirring process are further improved; constructing a stirring control performance verification chain by using the mixing proportion characteristics and the working performance constraint, and evaluating the performance verification result of the concrete production process and providing guidance for optimization and adjustment; the target stirring control decision is transmitted to the concrete production management end through encryption, so that the safety and confidentiality of the decision are ensured, meanwhile, stirring control is carried out according to the decision, and the production process of accurately controlling the target concrete is realized. In summary, the method for optimizing the concrete production process solves the problem of unstable efficiency and quality in the traditional concrete production process by introducing a systematic stirring control method and a performance verification chain, realizes a more accurate, efficient and controllable concrete stirring process, and improves the efficiency and quality of the concrete production process.
The foregoing description is only an overview of the technical solutions of the present application, and may be implemented according to the content of the specification in order to make the technical means of the present application more clearly understood, and in order to make the above-mentioned and other objects, features and advantages of the present application more clearly understood, the following detailed description of the present application will be given.
Drawings
Fig. 1 is a schematic flow chart of a method for optimizing a concrete production process according to an embodiment of the present application;
fig. 2 is a schematic structural diagram of a concrete production process optimization system according to an embodiment of the present application.
Reference numerals illustrate: the device comprises a characteristic acquisition module 10, a performance constraint acquisition module 20, a control phase division module 30, a control molecule mining module 40, a verification chain construction module 50, a stirring control optimizing module 60 and a concrete stirring module 70.
Detailed Description
According to the method for optimizing the production process of the concrete, the technical problems that the efficiency is low and the quality is unstable due to the fact that a systematic method is lacked in the traditional concrete production process to control stirring and the adjustment is usually carried out by depending on an empirical judgment or trial-and-error method in order to achieve target working performance requirements are solved.
Having described the basic principles of the present application, various non-limiting embodiments of the present application will now be described in detail with reference to the accompanying drawings.
Example 1
As shown in fig. 1, an embodiment of the present application provides a method for optimizing a production process of concrete, the method including:
connecting a concrete production management end to obtain the mixing proportion characteristic of target concrete;
and establishing connection with a concrete production management system so as to acquire required data and information, and acquiring the mixing proportion characteristics of target concrete through interaction with a concrete production management end, wherein the mixing proportion characteristics relate to the information of the types, proportions, properties and the like of the used raw materials, and the information can be recorded by the concrete production management system. For different grades and different types of concrete, such as common grade concrete, high-strength concrete and ultra-high-strength concrete, the raw materials used by the concrete and the ultra-high-strength concrete have larger difference, so that the grade of the concrete, the proportion of the raw materials or other special requirements are required to be considered when the mixing proportion characteristics are obtained, wherein the type and the property requirements of the raw materials are determined according to the grade of target concrete; determining the proportion of each raw material in the concrete mixing proportion according to design requirements or standard specifications; if the target concrete has specific performance requirements, such as durability, crack resistance, etc., appropriate additives are added to the mix ratio or the properties of the raw materials are controlled.
The concrete production management end is interacted to obtain N working performance constraints corresponding to N working performance indexes of the target concrete, wherein N is a positive integer greater than 1;
the N working performance indexes and N working performance constraints are determined according to specific requirements, N is a positive integer greater than 1, and the indexes and constraint conditions can be customized according to the characteristics of the research object and the target concrete. And determining working performance indexes of the target concrete, wherein the working performance indexes comprise flowability, cohesiveness, water retention, uniformity and the like, and the working performance constraint corresponding to each working performance index is obtained through interaction with a concrete production management end, and is a set of coefficient ranges for describing the allowable working performance value ranges, for example, an allowable fluidity range or upper and lower limits of a liquid fineness modulus can be defined for the flowability indexes. And setting corresponding constraint conditions for each working performance index according to the obtained working performance constraint, wherein the conditions are used as the basis for optimizing the concrete mixing ratio subsequently.
Dividing the stirring control stages of the target concrete based on the mixing proportion characteristics and the N working performance constraints to obtain G stirring control stages, wherein G is a positive integer greater than 1;
Analyzing the obtained mixing proportion characteristic data, including the types, proportions and properties of raw materials used in the concrete, wherein the information is used for determining a specific stage required in the stirring process; according to the obtained working performance constraint, the allowable range of each working performance index is considered, for example, the fluidity index needs to be within a certain liquid fineness modulus range, the cohesiveness needs to reach a specific viscosity requirement, and the like. Based on the mix characteristics and performance constraints, the mix control phase of the target concrete is divided to ensure that the concrete can achieve the desired performance.
Illustratively, the method comprises a dry mixing stage, a wet mixing stage and a mixing stage, wherein the dry mixing stage is used for putting raw materials such as cement, sand, stone and the like into a stirrer for dry mixing so as to ensure uniform distribution of various raw materials; in the wet mixing stage, a proper amount of water is added on the basis of dry mixing, and wet mixing is carried out, so that the raw materials fully absorb water to form concrete; the mixing stage, in which the mixer is started on a wet mix basis, causes the mixer to begin to spin, mixing the raw materials, aids in further uniform mixing and formation of the desired concrete properties.
According to specific conditions, more stirring control stages can be defined, each stage can meet the requirements of working performance constraint and mixing proportion characteristics, and the number G of the finally determined stirring control stages is a positive integer greater than 1 so as to meet the process requirements in concrete production.
Digging stirring control molecules based on the mixing proportion characteristics and the G stirring control stages to obtain a stirring control molecule space;
further, performing agitation control molecule excavation based on the mix ratio characteristics and the G agitation control phases to obtain an agitation control molecule space, including:
sequencing the G stirring control stages according to a stirring control sequence to obtain a first stirring control stage and a second stirring control stage … G stirring control stage, wherein G is a positive integer, and G belongs to G;
based on the mixing proportion characteristics, carrying out data mining on the first stirring control stage to obtain a first stirring control domain;
randomly taking values based on the first stirring control domain to obtain a plurality of stirring first-order control atoms;
based on the mix proportion characteristics, respectively performing data mining on the g-th stirring control stage of the second stirring control stage … to obtain a second stirring control domain … g-th stirring control domain;
traversing the g-th stirring control domain of the second stirring control domain … to carry out random value taking to obtain a plurality of stirring second-order control atoms … and a plurality of stirring g-order control atoms;
the stirring control molecules are obtained by randomly combining the stirring control atoms g based on the stirring first-order control atoms and the stirring second-order control atoms …, and are added to the stirring control molecule space, and each stirring control molecule comprises one stirring first-order control atom random and one stirring second-order control atom … random and one stirring g-order control atom random.
And analyzing the previously divided stirring control stages, and determining the execution sequence of each stirring control stage according to the concrete production process and the required mixing effect based on the concrete raw material characteristics, the concrete performance requirements and the actual operation experience. And sequencing the G stirring control stages according to the determined stirring control sequence, and marking a sequence number for each stage, for example, a first stirring control stage, a second stirring control stage and so on until a G stirring control stage, wherein G is a positive integer and belongs to G.
And (3) sorting the blending ratio characteristic data related to the first stirring control stage, and defining a stirring control domain, wherein the stirring control domain is a value range of a set of parameters or conditions and is used for guiding the operation of the first stirring control stage. The data mining technology is used for analyzing the matching characteristic data, so that the association relation and influence factors among different parameters can be found. And determining the value ranges of the first stirring control domain based on the analysis result, wherein the value ranges can be used as the basis for guiding parameters required in actual operation.
For example, in the first mixing control phase, it is desirable to determine the effect of cement input and sand to a certain performance index of the concrete, such as flowability, by data mining, and by collecting and analyzing the relevant data for modeling, a feasible first mixing control domain, namely, a suitable cement input range and a reasonable sand ratio, can be obtained.
On the basis of the first stirring control domain, the first stirring control parameters to be set are determined, and the parameters are key factors influencing the concrete stirring process, such as cement input amount, sand and stone proportion and the like. For each stirring first-order control parameter, determining the value range according to the definition of the first stirring control domain.
And in the determined value range, randomly taking the value of each stirring first-order control parameter by using a random number generation method, and repeating the process for a plurality of times according to the required number of stirring first-order control atoms. And recording the mixing first-order control parameter combination obtained randomly each time to form a plurality of mixing first-order control atoms, wherein each atom is obtained by randomly taking values in a first mixing control domain, and the atoms are used for subsequent optimization analysis so as to evaluate the performance of the concrete and find the optimal mixing control strategy.
And (3) sorting the blending ratio characteristic data related to each stirring control stage, determining the stirring control domain of each stirring control stage, adopting the same method to perform data mining on the g-th stirring control stage of the second stirring control stage …, analyzing the blending ratio characteristic data, and determining the value range of the stirring control domain of each stirring control stage, namely, the second stirring control domain to the g-th stirring control domain, based on the analysis result, wherein each stirring control domain is obtained by performing data mining according to the blending ratio characteristic of the corresponding stirring control stage.
And defining stirring second-order control parameters to be set to stirring g-order control parameters for each stirring control stage, determining a value range of each stirring control parameter according to the definition of a corresponding stirring control domain, traversing and randomly taking values according to the determined value range for each stirring control parameter, and combining and recording the stirring control parameters obtained each time to form a plurality of stirring second-order control atoms to a plurality of stirring g-order control atoms.
A space for storing the agitation control molecules is created, which may be a list structure. For each agitation control molecule, randomly selecting one agitation first order control atom, one agitation second order control atom, and so on from a plurality of agitation first order control atoms and a plurality of agitation second order control atoms to a plurality of agitation g order control atoms, until one agitation g order control atom, by randomly selecting, generating one agitation control molecule representing one agitation control strategy combination. The generated agitation control molecule is added to the agitation control molecule space.
The above steps are repeated as many times as necessary to create and add a plurality of different agitation control molecules to the space of agitation control molecules, which represent different combinations of agitation control strategies, each consisting of randomly selected first order control atoms, second order control atoms, and so on, until the g-order control atoms are agitated.
Further, based on the mix characteristics, performing data mining on the first agitation control stage to obtain a first agitation control domain, including:
taking the mixing proportion characteristic as a retrieval constraint and taking the stirring control record data of the first stirring control stage as a retrieval target;
according to the retrieval constraint and the retrieval target, retrieving concrete mixing control data to obtain a plurality of first-order mixing control record data;
performing support degree calculation on the plurality of first-order stirring control record data to obtain a plurality of first-order control support degrees, and calculating a plurality of first-order control confidence degrees according to the plurality of first-order control support degrees;
screening the plurality of first-order stirring control record data according to the plurality of first-order control confidence levels based on a preset confidence level constraint to obtain a first-order stirring control record screening result meeting the preset confidence level constraint;
and carrying out the maximum calibration based on the first-order stirring control record screening result to obtain a first-order stirring maximum calibration result, and constructing the first stirring control domain based on the first-order stirring maximum calibration result.
Recorded data relating to the agitation control of the first agitation control stage, including agitation speed, agitation time, etc., are collected, and may be from previous agitation process recordings or experimental data. In combination with the mix characteristics, one or more mix characteristics are determined as search constraints, such as cement input, sand proportion, etc. Using the selected mix characteristics as a search constraint, data points satisfying the constraint are screened out in the blending control record data, which facilitates determining associations between blending parameters, such as blending speed and blending time, and mix characteristics.
According to the mixing proportion characteristics and the stirring control target of the first stirring control stage, search constraints are clearly defined, including a specific mixing proportion range, a stirring speed range, a stirring time range and the like.
And screening and searching the concrete mixing control data by using the defined searching constraint, and extracting a plurality of first-order mixing control record data meeting the constraint conditions according to the searching result, wherein the record data comprises information such as mixing parameters, time stamps, mixing proportion characteristics and the like related to the first mixing control stage.
The first order agitation control record data is considered as a set of items, where each item represents an agitation control parameter or condition. For each first-order stirring control item set, calculating the occurrence frequency of the first-order stirring control item set in all recorded data, namely the support degree, wherein the support degree represents the occurrence number of the first-order stirring control item set in the data; and calculating by using the support degree and the total record quantity, and dividing the support degree of the item sets by the total record quantity to obtain the confidence degree of each first-order stirring control item set, wherein the confidence degree refers to the probability that other item sets are simultaneously appeared when a specific item set appears.
For each first-order stirring control item set, recording the support degree and the confidence degree of each first-order stirring control item set, and obtaining a plurality of first-order control support degrees and confidence degrees, wherein the support degrees provide a measure for measuring the occurrence frequency of a certain first-order stirring control item set in data, and the confidence degrees represent the correlation degree among item sets.
And defining the expected confidence constraint according to specific requirements and targets, and acquiring the preset confidence constraint. For each first-order stirring control record data, checking whether the corresponding first-order control confidence coefficient meets the preset confidence coefficient constraint, and if the confidence coefficient meets the requirement, adding the record data into a screening result; otherwise, it is excluded. Traversing all first-order stirring control record data, and screening according to the confidence coefficient constraint, so as to finally obtain a first-order stirring control record screening result meeting the preset confidence coefficient constraint.
For each index, such as stirring speed and stirring time, corresponding values are extracted from the first-order stirring control record screening result, and the maximum value and the minimum value of each index are determined by comparing the extracted values. Correlating the determined maximum and minimum values with corresponding indices to form a first order blending maximum calibration result, e.g. a blending speed maximumThe method comprises the steps of carrying out a first treatment on the surface of the Minimum stirring speed->The method comprises the steps of carrying out a first treatment on the surface of the Maximum stirring time->The method comprises the steps of carrying out a first treatment on the surface of the Minimum stirring time->。
Based on the first order blending maximum calibration result, a first blending control domain is constructed, i.e. a reasonable value range of each index is defined, which is realized by using the interval between the maximum value and the minimum value, for example, the feasible range of the blending speed is from To->The possible range of stirring times is from +.>To->。
The acquisition of the first stirring control domain is helpful for guiding the setting of each parameter in the stirring process, so that the setting is kept in a reasonable range, and better stirring effect and concrete quality are realized.
Constructing a stirring control performance verification chain based on the mixing proportion characteristics and the N working performance constraints;
further, constructing a stir control performance validation chain based on the mix characteristics and the N performance constraints, comprising:
carrying out random numbering based on the N working performance constraints to obtain a first working performance constraint and a second working performance constraint … nth working performance constraint, wherein N is a positive integer, and N belongs to N;
based on the mixing proportion characteristics, constructing a verification node for the first working performance constraint to obtain a first stirring control performance verification node;
based on the mix proportion characteristics, respectively constructing verification nodes of the nth working performance constraint of the second working performance constraint … to generate a second stirring control performance verification node … nth stirring control performance verification node;
and performing identification integration on the first stirring control performance verification node, the second stirring control performance verification node … and the nth stirring control performance verification node based on the N working performance indexes to generate the stirring control performance verification chain.
For the N operational performance constraints obtained, they are numbered, from 1 to N, the numbers 1 to N are randomly ordered using a randomization method, ensuring that each number appears and only appears once, to create a random sequence of numbers.
And sequentially taking out corresponding working performance constraints according to the random number sequence, for example, if the random number sequence is 3, 1 and 2, the first working performance constraint is the third constraint in the original list, the second working performance constraint is the first constraint in the original list, and so on until the nth working performance constraint, wherein N is a positive integer and N belongs to N. Such a random numbering scheme may randomly order the performance constraints.
Training is performed based on a fully connected neural network, a first working performance predictor and a first working performance verifier are obtained, the first working performance predictor and the first working performance verifier are connected, and the first stirring control performance verification node is generated.
And constructing a second working performance predictor and a second working performance verifier by adopting the same method until the nth working performance predictor and the nth working performance verifier are adopted, and generating a second stirring control performance verification node until the nth stirring control performance verification node.
Specific indexes for evaluation and integration are well defined according to the work performance indexes, and include strength, fluidity, slump, and the like. And selecting proper identification integration methods, such as a weighted average method, a rule combination method, model fusion and the like, for the first to nth agitation control performance verification nodes, identifying the first to nth agitation control performance verification nodes by using corresponding working performance indexes, and integrating identification results carried out for each verification node to form an agitation control performance verification chain, wherein the verification chain represents the sequence and combination of the agitation control performance verification nodes meeting specific requirements under different working performance indexes.
Further, based on the mix characteristic, constructing a verification node for the first performance constraint to obtain a first stirring control performance verification node, including:
based on the N working performance indexes, matching a first working performance index corresponding to the first working performance constraint;
performing concrete production record tracing on the concrete production management end based on the first working performance index to obtain a concrete mix characteristic record data sequence, a concrete mixing control record data sequence and a concrete first working performance record data sequence;
The concrete mixing proportion characteristic record data sequence and the concrete stirring control record data sequence are used as input data, the first concrete working performance record data sequence is used as output supervision data, the fully-connected neural network is trained, and output accuracy is obtained when training is performed for preset times;
if the output accuracy is greater than or equal to the preset accuracy, a first working performance predictor is obtained;
constructing a first working performance verifier based on the first working performance constraint, wherein the first working performance verifier comprises a first working performance verification operator, the first working performance verification operator is a first node performance verification result obtained when a first working performance prediction coefficient output by the first working performance predictor meets the first working performance constraint is 1, and the first node performance verification result obtained when the first working performance prediction coefficient output by the first working performance predictor does not meet the first working performance constraint is 0;
and connecting the first working performance predictor with the first working performance verifier to generate the first stirring control performance verification node.
The index matching the first performance constraint is found from the N performance indexes, and the matching method may be to directly compare the constraint with the index value or to perform matching using an algorithm. And taking the successfully matched working performance index as an index corresponding to the first working performance constraint, wherein the index represents a specific working performance index related to the first working performance constraint.
The specific parameters to be traced are defined explicitly according to the first performance index, which may be the compressive strength of the concrete, for example, if the strength of the concrete is concerned. In the concrete production management end, according to the first working performance index, the related records in the concrete production process are traced, including records of concrete mixing proportion, stirring control parameters, first working performance test results and the like.
Extracting data related to the mixing proportion characteristic from the concrete production record to form a concrete mixing proportion characteristic record data sequence, wherein the data comprise cement input quantity, sand and stone proportion, admixture consumption and the like; extracting data related to the stirring control from the concrete production record to form a concrete stirring control record data sequence, wherein the data comprises stirring time, stirring speed, stirrer rotating speed and the like; data relating to the first performance characteristic is extracted from the concrete production record to form a concrete first performance characteristic record data sequence, wherein the data comprises a compressive strength test result, a tensile strength test result and the like.
These recorded data sequences help analyze correlations between mix characteristics, mix control, and first performance properties during concrete production to guide concrete quality control and optimize the mixing process.
And taking the concrete mixing proportion characteristic record data sequence and the concrete stirring control record data sequence as input data, taking the first concrete working performance record data sequence as output supervision data, wherein the input data and the output data have the same sample number and corresponding relation. And selecting a proper fully-connected neural network model structure, wherein the fully-connected neural network model structure comprises an input layer, a hidden layer and an output layer, and designing the number of layers of the neural network, the number of neurons of each layer, an activation function and the like according to specific problems and data characteristics. An appropriate loss function is selected to measure the difference between the neural network predicted result and the true output, such as the mean square error, while an appropriate optimization algorithm, such as the random gradient descent, is selected.
The data set is divided into a training set and a verification set, the training set is used for training the neural network model, when each training preset time is finished, for example, 50 times, the specific times are defined according to actual requirements, the verification set is used for evaluating the output accuracy of the model by calculating the difference between the predicted value and the actual value. Based on the results of the loss function, a back-propagation algorithm is used to calculate the gradient and an optimizer is used to update parameters of the neural network model to minimize the loss function.
The above steps are circularly executed until the preset training times, for example, 500 times, are reached, and the specific times are defined according to the actual requirements. After each training preset time is finished, the change of the output accuracy is recorded and evaluated.
Defining a preset accuracy as a target, wherein the preset accuracy is a minimum accuracy threshold value which is expected to be achieved by the neural network, and the threshold value is determined according to specific application scenes and requirements, for example, the preset accuracy is set to be 90%.
According to the method described above, after each training preset time is finished, the output accuracy of the neural network model is evaluated by using the verification set, the output accuracy of each training preset time is compared with the preset accuracy, if the output accuracy is greater than or equal to the preset accuracy, which indicates that the neural network model has reached or exceeded the set target, the trained neural network model can be used as a first working performance predictor, and the predictor can be used for predicting new concrete mix characteristic record data and stirring control record data to obtain corresponding first working performance prediction results.
According to the first working performance constraint, a first working performance verifier is designed, the verifier comprises a first working performance verification operator, and the first working performance verification operator judges a performance verification result of the first node by comparing a first working performance prediction coefficient output by the first working performance predictor with the first working performance constraint.
Inputting the j-th stirring verification data into a first working performance predictor to obtain a first working performance prediction coefficient corresponding to the j-th stirring verification data, and if the first working performance prediction coefficient meets the first working performance constraint, the performance verification result of the first node is 1, which indicates that the first node passes the performance verification; and if the first working performance prediction coefficient does not meet the first working performance constraint, the performance verification result of the first node is 0, which indicates that the first node fails the performance verification.
This verifier may help evaluate and verify the performance of the first node, with subsequent operations based on the performance verification result to ensure that the first node meets certain operational performance requirements.
The first working performance predictor and the first working performance verifier are connected to form a first stirring control performance verification node, and the node has the capability of predicting the first working performance and the function of verifying whether the first working performance meets constraint or not, so that the first working performance can be predicted in real time in the concrete stirring process and verified, potential problems can be found and corrected in time, and the performance of concrete stirring control is ensured to meet the requirements.
Based on the mixing proportion characteristic and the stirring control performance verification chain, executing stirring control optimizing of the target concrete according to the stirring control molecular space to obtain a target stirring control decision;
further, based on the mix characteristics and the mixing control performance verification chain, performing mixing control optimization of the target concrete according to the mixing control molecular space, obtaining a target mixing control decision, including:
randomly selecting based on the stirring control molecule space to obtain a j-th stirring control molecule;
generating j-th agitation verification data based on the mix characteristics and the j-th agitation control molecule;
performing stirring control performance verification on the j-th stirring verification data based on the stirring control performance verification chain to obtain a j-th stirring performance verification chain, wherein the j-th stirring performance verification chain comprises N node performance verification results corresponding to the j-th stirring verification data;
judging whether the performance verification results of N nodes in the j-th stirring performance verification chain are 1;
and if the performance verification results of the N nodes in the j-th stirring performance verification chain are all 1, outputting the j-th stirring control molecule as the target stirring control decision.
The selection range of the j-th agitation controlling molecule may be defined as the whole agitation controlling molecule space or may be defined as a specific subspace according to the specific circumstances. A randomly selected method is used to select and obtain a j-th agitation control molecule from the selected range, which represents the particular control parameter selected during agitation.
The blending characteristics and the j-th agitation control molecules are combined to generate j-th agitation verification data, which means that the blending characteristics and the j-th agitation control molecules are taken as inputs to form one data sample, for example, each parameter value of the blending characteristics may be taken as a part of the inputs, and the j-th agitation control molecules may be taken as another part, and the values of the blending characteristics and the j-th agitation control molecules may be combined in the form of vectors or matrices for performance verification in the agitation process.
According to the j-th agitation verification data, performance verification is performed for each node by a method of an agitation control performance verification chain including a series of nodes each corresponding to a specific aspect of the j-th agitation verification data. For each node, inputting the j-th stirring verification data into the corresponding stirring control performance verification node for performance verification, and obtaining a node performance verification result, wherein the node performance verification result comprises passing performance verification and failing performance verification. The performance verification results for each node are combined in order to form a j-th agitation performance verification chain that provides performance verification results for each aspect of the j-th agitation verification data.
And (3) according to the j-th stirring performance verification chain generated in the previous step, the chain comprises the performance verification results of N nodes. Checking the performance verification results of each node one by one, and if the performance verification results of all N nodes are 1, judging that the performance verification results of N nodes in the j-th stirring performance verification chain are 1; if the performance verification result of any node is not 1, that is, at least one node fails the performance verification, it can be concluded that the performance verification results of the N nodes in the j-th stirring performance verification chain are not uniformly 1. This will provide an overall result of performance verification in different aspects with respect to the jth agitation verification data.
Checking whether the performance verification results of the N nodes in the j-th stirring performance verification chain are all 1, and if the performance verification results of all the nodes are all 1, which means that the stirring control performance of the j-th stirring verification data in all aspects is verified, taking the j-th stirring control molecule as the output of the target stirring control decision, which means that the j-th stirring control molecule is considered to be effective and can be used in the actual stirring process.
Further, determining whether the performance verification results of the N nodes in the j-th stirring performance verification chain are all 1, further includes:
If the performance verification results of N nodes in the j-th stirring performance verification chain are not equal to 1, obtaining j+1-th stirring control molecules based on the stirring control molecule space;
generating j+1th agitation verification data based on the mix characteristics and the j+1th agitation control molecule;
performing stirring control performance verification on the j+1th stirring verification data based on the stirring control performance verification chain to obtain a j+1th stirring performance verification chain;
judging whether all node performance verification results in the j+1th stirring performance verification chain are 1 or not;
if the performance verification results of all nodes in the j+1 stirring performance verification chain are 1, outputting the j+1 stirring control molecules as the target stirring control decision;
and if the performance verification results of all nodes in the j+1 stirring performance verification chain are not equal to 1, continuing to perform iterative optimization on the stirring control molecular space until the target stirring control decision is generated.
If the performance verification result of the N nodes in the j-th stirring performance verification chain is not equal to 1, the j-th stirring verification data does not pass the performance verification in some aspects. In this case, the j+1th agitation control molecule may be obtained based on the agitation control molecule space in an attempt to improve the performance of the agitation process.
Specifically, the range of the stirring control molecule space including adjustable stirring parameters such as stirring time, stirring speed, etc. is confirmed. According to the space of the stirring control molecules, the j+1th stirring control molecule is generated by using a proper method, for example, an optimization algorithm and a genetic algorithm are adopted, and new stirring control molecules are searched in the space of the stirring control molecules. And obtaining a specific value according to the generated j+1th stirring control molecule, wherein the specific value represents the improved stirring control parameter. This can help improve the agitation process, and improve the results of performance verification by adjusting the agitation control parameters.
And adopting the same processing mode as the j-th stirring control molecule to perform stirring control performance verification and node performance verification result judgment on the j+1-th stirring control molecule until the target stirring control decision is generated, and for the sake of simplicity of the description, the description is omitted.
And encrypting and transmitting the target stirring control decision to the concrete production management end, and stirring the target concrete according to the target stirring control decision.
By encrypting the target blending control decision using appropriate encryption algorithms and protocols, this ensures confidentiality and security during transmission. And transmitting the encrypted target stirring control decision to a concrete production management end, decrypting the received encrypted decision by using a corresponding decryption algorithm and a key at the concrete production management end, and restoring the original target stirring control decision so that the original target stirring control decision can be further processed and used. When the target stirring control decision is decrypted, the concrete production management end guides the actual concrete stirring process according to the decision, and the concrete production management end comprises the steps of adjusting stirring parameters such as stirring time, stirring speed and the like so as to ensure that concrete is stirred according to target requirements.
In summary, the method and the system for optimizing the production process of the concrete provided by the embodiment of the application have the following technical effects:
1. according to the mixing proportion characteristics of target concrete and the constraint of working performance, dividing the concrete production process into a plurality of stirring control stages, so that the stirring process of the concrete is better controlled;
2. based on the mixing proportion characteristics and the stirring control stage, an adjustable stirring parameter is obtained by exploring a stirring control molecular space, and the controllability and the efficiency of the stirring process are further improved;
3. constructing a stirring control performance verification chain by using the mixing proportion characteristics and the working performance constraint, and evaluating the performance verification result of the concrete production process and providing guidance for optimization and adjustment;
4. the target stirring control decision is transmitted to the concrete production management end through encryption, so that the safety and confidentiality of the decision are ensured, meanwhile, stirring control is carried out according to the decision, and the production process of accurately controlling the target concrete is realized.
In summary, the method for optimizing the concrete production process solves the problem of unstable efficiency and quality in the traditional concrete production process by introducing a systematic stirring control method and a performance verification chain, realizes a more accurate, efficient and controllable concrete stirring process, and improves the efficiency and quality of the concrete production process.
Example two
Based on the same inventive concept as the production process optimization method of a concrete in the foregoing embodiments, as shown in fig. 2, the present application provides a production process optimization system of a concrete, the system comprising:
the characteristic acquisition module 10 is used for connecting a concrete production management end to acquire the mixing proportion characteristic of target concrete;
the performance constraint acquisition module 20 is used for interacting the concrete production management end to obtain N working performance constraints corresponding to N working performance indexes of the target concrete, wherein N is a positive integer greater than 1;
the control phase division module 30 is configured to divide the stirring control phase of the target concrete based on the mix ratio feature and the N working performance constraints, to obtain G stirring control phases, where G is a positive integer greater than 1;
a control molecule excavating module 40, wherein the control molecule excavating module 40 is used for carrying out stirring control molecule excavating based on the mixing ratio characteristics and the G stirring control stages to obtain a stirring control molecule space;
a verification chain construction module 50, wherein the verification chain construction module 50 is used for constructing a stirring control performance verification chain based on the mix proportion characteristics and the N working performance constraints;
The stirring control optimizing module 60, wherein the stirring control optimizing module 60 is used for executing stirring control optimizing of the target concrete according to the stirring control molecular space based on the mixing ratio characteristic and the stirring control performance verification chain to obtain a target stirring control decision;
the concrete mixing module 70 is configured to encrypt and transmit the target mixing control decision to the concrete production management end, and mix the target concrete according to the target mixing control decision by the concrete mixing module 70.
Further, the system also comprises an acquisition module for executing the following operation steps:
sequencing the G stirring control stages according to a stirring control sequence to obtain a first stirring control stage and a second stirring control stage … G stirring control stage, wherein G is a positive integer, and G belongs to G;
based on the mixing proportion characteristics, carrying out data mining on the first stirring control stage to obtain a first stirring control domain;
randomly taking values based on the first stirring control domain to obtain a plurality of stirring first-order control atoms;
based on the mix proportion characteristics, respectively performing data mining on the g-th stirring control stage of the second stirring control stage … to obtain a second stirring control domain … g-th stirring control domain;
Traversing the g-th stirring control domain of the second stirring control domain … to carry out random value taking to obtain a plurality of stirring second-order control atoms … and a plurality of stirring g-order control atoms;
the stirring control molecules are obtained by randomly combining the stirring control atoms g based on the stirring first-order control atoms and the stirring second-order control atoms …, and are added to the stirring control molecule space, and each stirring control molecule comprises one stirring first-order control atom random and one stirring second-order control atom … random and one stirring g-order control atom random.
Further, the system also includes a first agitation control domain acquisition module to perform the following operational steps:
taking the mixing proportion characteristic as a retrieval constraint and taking the stirring control record data of the first stirring control stage as a retrieval target;
according to the retrieval constraint and the retrieval target, retrieving concrete mixing control data to obtain a plurality of first-order mixing control record data;
performing support degree calculation on the plurality of first-order stirring control record data to obtain a plurality of first-order control support degrees, and calculating a plurality of first-order control confidence degrees according to the plurality of first-order control support degrees;
Screening the plurality of first-order stirring control record data according to the plurality of first-order control confidence levels based on a preset confidence level constraint to obtain a first-order stirring control record screening result meeting the preset confidence level constraint;
and carrying out the maximum calibration based on the first-order stirring control record screening result to obtain a first-order stirring maximum calibration result, and constructing the first stirring control domain based on the first-order stirring maximum calibration result.
Further, the system also comprises a target stirring control decision acquisition module for executing the following operation steps:
randomly selecting based on the stirring control molecule space to obtain a j-th stirring control molecule;
generating j-th agitation verification data based on the mix characteristics and the j-th agitation control molecule;
performing stirring control performance verification on the j-th stirring verification data based on the stirring control performance verification chain to obtain a j-th stirring performance verification chain, wherein the j-th stirring performance verification chain comprises N node performance verification results corresponding to the j-th stirring verification data;
judging whether the performance verification results of N nodes in the j-th stirring performance verification chain are 1;
And if the performance verification results of the N nodes in the j-th stirring performance verification chain are all 1, outputting the j-th stirring control molecule as the target stirring control decision.
Further, the system also comprises a performance verification chain construction module for executing the following operation steps:
carrying out random numbering based on the N working performance constraints to obtain a first working performance constraint and a second working performance constraint … nth working performance constraint, wherein N is a positive integer, and N belongs to N;
based on the mixing proportion characteristics, constructing a verification node for the first working performance constraint to obtain a first stirring control performance verification node;
based on the mix proportion characteristics, respectively constructing verification nodes of the nth working performance constraint of the second working performance constraint … to generate a second stirring control performance verification node … nth stirring control performance verification node;
and performing identification integration on the first stirring control performance verification node, the second stirring control performance verification node … and the nth stirring control performance verification node based on the N working performance indexes to generate the stirring control performance verification chain.
Further, the system further comprises a first authentication node acquisition module to perform the following operation steps:
Based on the N working performance indexes, matching a first working performance index corresponding to the first working performance constraint;
performing concrete production record tracing on the concrete production management end based on the first working performance index to obtain a concrete mix characteristic record data sequence, a concrete mixing control record data sequence and a concrete first working performance record data sequence;
the concrete mixing proportion characteristic record data sequence and the concrete stirring control record data sequence are used as input data, the first concrete working performance record data sequence is used as output supervision data, the fully-connected neural network is trained, and output accuracy is obtained when training is performed for preset times;
if the output accuracy is greater than or equal to the preset accuracy, a first working performance predictor is obtained;
constructing a first working performance verifier based on the first working performance constraint, wherein the first working performance verifier comprises a first working performance verification operator, the first working performance verification operator is a first node performance verification result obtained when a first working performance prediction coefficient output by the first working performance predictor meets the first working performance constraint is 1, and the first node performance verification result obtained when the first working performance prediction coefficient output by the first working performance predictor does not meet the first working performance constraint is 0;
And connecting the first working performance predictor with the first working performance verifier to generate the first stirring control performance verification node.
Further, the system also comprises an iterative optimization module for executing the following operation steps:
if the performance verification results of N nodes in the j-th stirring performance verification chain are not equal to 1, obtaining j+1-th stirring control molecules based on the stirring control molecule space;
generating j+1th agitation verification data based on the mix characteristics and the j+1th agitation control molecule;
performing stirring control performance verification on the j+1th stirring verification data based on the stirring control performance verification chain to obtain a j+1th stirring performance verification chain;
judging whether all node performance verification results in the j+1th stirring performance verification chain are 1 or not;
if the performance verification results of all nodes in the j+1 stirring performance verification chain are 1, outputting the j+1 stirring control molecules as the target stirring control decision;
and if the performance verification results of all nodes in the j+1 stirring performance verification chain are not equal to 1, continuing to perform iterative optimization on the stirring control molecular space until the target stirring control decision is generated.
The foregoing detailed description of a concrete production process optimization method and system of the present embodiment will be apparent to those skilled in the art, and the device disclosed in the embodiments corresponds to the method disclosed in the embodiments, so that the description is simpler, and the relevant places refer to the description of the method section.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (6)
1. A method for optimizing a production process of concrete, the method comprising:
connecting a concrete production management end to obtain the mixing proportion characteristic of target concrete;
the concrete production management end is interacted to obtain N working performance constraints corresponding to N working performance indexes of the target concrete, wherein N is a positive integer greater than 1;
Dividing the stirring control stages of the target concrete based on the mixing proportion characteristics and the N working performance constraints to obtain G stirring control stages, wherein G is a positive integer greater than 1;
digging stirring control molecules based on the mixing proportion characteristics and the G stirring control stages to obtain a stirring control molecule space;
constructing a stirring control performance verification chain based on the mixing proportion characteristics and the N working performance constraints;
based on the mixing proportion characteristic and the stirring control performance verification chain, executing stirring control optimizing of the target concrete according to the stirring control molecular space to obtain a target stirring control decision;
encrypting and transmitting the target stirring control decision to the concrete production management end, and stirring the target concrete according to the target stirring control decision;
and performing agitation control molecule excavation based on the mix ratio characteristics and the G agitation control phases to obtain an agitation control molecule space, comprising:
sequencing the G stirring control stages according to a stirring control sequence to obtain a first stirring control stage and a second stirring control stage … G stirring control stage, wherein G is a positive integer, and G belongs to G;
Based on the mixing proportion characteristics, carrying out data mining on the first stirring control stage to obtain a first stirring control domain;
randomly taking values based on the first stirring control domain to obtain a plurality of stirring first-order control atoms;
based on the mix proportion characteristics, respectively performing data mining on the g-th stirring control stage of the second stirring control stage … to obtain a second stirring control domain … g-th stirring control domain;
traversing the g-th stirring control domain of the second stirring control domain … to carry out random value taking to obtain a plurality of stirring second-order control atoms … and a plurality of stirring g-order control atoms;
randomly combining the plurality of stirring g-order control atoms based on the plurality of stirring first-order control atoms and the plurality of stirring second-order control atoms … to obtain a plurality of stirring control molecules, adding the plurality of stirring control molecules to the stirring control molecule space, wherein each stirring control molecule comprises one stirring first-order control atom at random and one stirring g-order control atom at random and one stirring second-order control atom at random …;
based on the mix proportion feature, performing data mining on the first stirring control stage to obtain a first stirring control domain, including:
Taking the mixing proportion characteristic as a retrieval constraint and taking the stirring control record data of the first stirring control stage as a retrieval target;
according to the retrieval constraint and the retrieval target, retrieving concrete mixing control data to obtain a plurality of first-order mixing control record data;
performing support degree calculation on the plurality of first-order stirring control record data to obtain a plurality of first-order control support degrees, and calculating a plurality of first-order control confidence degrees according to the plurality of first-order control support degrees;
screening the plurality of first-order stirring control record data according to the plurality of first-order control confidence levels based on a preset confidence level constraint to obtain a first-order stirring control record screening result meeting the preset confidence level constraint;
and carrying out the maximum calibration based on the first-order stirring control record screening result to obtain a first-order stirring maximum calibration result, and constructing the first stirring control domain based on the first-order stirring maximum calibration result.
2. The method of claim 1, wherein performing a mix control optimization of the target concrete based on the mix ratio characteristics and the mix control performance validation chain according to the mix control molecular space, obtaining a target mix control decision comprises:
Randomly selecting based on the stirring control molecule space to obtain a j-th stirring control molecule;
generating j-th agitation verification data based on the mix characteristics and the j-th agitation control molecule;
performing stirring control performance verification on the j-th stirring verification data based on the stirring control performance verification chain to obtain a j-th stirring performance verification chain, wherein the j-th stirring performance verification chain comprises N node performance verification results corresponding to the j-th stirring verification data;
judging whether the performance verification results of N nodes in the j-th stirring performance verification chain are 1;
and if the performance verification results of the N nodes in the j-th stirring performance verification chain are all 1, outputting the j-th stirring control molecule as the target stirring control decision.
3. The method of claim 1, wherein constructing a stir control performance validation chain based on the mix characteristics and the N performance constraints comprises:
carrying out random numbering based on the N working performance constraints to obtain a first working performance constraint and a second working performance constraint … nth working performance constraint, wherein N is a positive integer, and N belongs to N;
based on the mixing proportion characteristics, constructing a verification node for the first working performance constraint to obtain a first stirring control performance verification node;
Based on the mix proportion characteristics, respectively constructing verification nodes of the nth working performance constraint of the second working performance constraint … to generate a second stirring control performance verification node … nth stirring control performance verification node;
and performing identification integration on the first stirring control performance verification node, the second stirring control performance verification node … and the nth stirring control performance verification node based on the N working performance indexes to generate the stirring control performance verification chain.
4. A method according to claim 3, wherein validating the first performance constraint based on the mix characteristics comprises:
based on the N working performance indexes, matching a first working performance index corresponding to the first working performance constraint;
performing concrete production record tracing on the concrete production management end based on the first working performance index to obtain a concrete mix characteristic record data sequence, a concrete mixing control record data sequence and a concrete first working performance record data sequence;
the concrete mixing proportion characteristic record data sequence and the concrete stirring control record data sequence are used as input data, the first concrete working performance record data sequence is used as output supervision data, the fully-connected neural network is trained, and output accuracy is obtained when training is performed for preset times;
If the output accuracy is greater than or equal to the preset accuracy, a first working performance predictor is obtained;
constructing a first working performance verifier based on the first working performance constraint, wherein the first working performance verifier comprises a first working performance verification operator, the first working performance verification operator is a first node performance verification result obtained when a first working performance prediction coefficient output by the first working performance predictor meets the first working performance constraint is 1, and the first node performance verification result obtained when the first working performance prediction coefficient output by the first working performance predictor does not meet the first working performance constraint is 0;
and connecting the first working performance predictor with the first working performance verifier to generate the first stirring control performance verification node.
5. The method of claim 2, wherein determining whether the N node performance verification results in the j-th agitation performance verification chain are all 1 further comprises:
if the performance verification results of N nodes in the j-th stirring performance verification chain are not equal to 1, obtaining j+1-th stirring control molecules based on the stirring control molecule space;
Generating j+1th agitation verification data based on the mix characteristics and the j+1th agitation control molecule;
performing stirring control performance verification on the j+1th stirring verification data based on the stirring control performance verification chain to obtain a j+1th stirring performance verification chain;
judging whether all node performance verification results in the j+1th stirring performance verification chain are 1 or not;
if the performance verification results of all nodes in the j+1 stirring performance verification chain are 1, outputting the j+1 stirring control molecules as the target stirring control decision;
and if the performance verification results of all nodes in the j+1 stirring performance verification chain are not equal to 1, continuing to perform iterative optimization on the stirring control molecular space until the target stirring control decision is generated.
6. A process optimization system for concrete, characterized by implementing a process optimization method for concrete according to any one of claims 1 to 5, comprising:
the characteristic acquisition module is used for connecting a concrete production management end to obtain the mixing proportion characteristic of target concrete;
the performance constraint acquisition module is used for interacting the concrete production management end to obtain N working performance constraints corresponding to N working performance indexes of the target concrete, wherein N is a positive integer greater than 1;
The control phase division module is used for carrying out stirring control phase division on the target concrete based on the mixing proportion characteristics and the N working performance constraints to obtain G stirring control phases, wherein G is a positive integer greater than 1;
the control molecule excavating module is used for carrying out stirring control molecule excavating based on the mixing proportion characteristics and the G stirring control stages to obtain a stirring control molecule space;
the verification chain construction module is used for constructing a stirring control performance verification chain based on the mixing proportion characteristics and the N working performance constraints;
the stirring control optimizing module is used for executing stirring control optimizing of the target concrete according to the stirring control molecular space based on the mixing ratio characteristics and the stirring control performance verification chain to obtain a target stirring control decision;
and the concrete stirring module is used for encrypting and transmitting the target stirring control decision to the concrete production management end, and stirring the target concrete according to the target stirring control decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311446632.6A CN117162263B (en) | 2023-11-02 | 2023-11-02 | Method and system for optimizing concrete production process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311446632.6A CN117162263B (en) | 2023-11-02 | 2023-11-02 | Method and system for optimizing concrete production process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117162263A CN117162263A (en) | 2023-12-05 |
| CN117162263B true CN117162263B (en) | 2023-12-29 |
Family
ID=88941589
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311446632.6A Active CN117162263B (en) | 2023-11-02 | 2023-11-02 | Method and system for optimizing concrete production process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117162263B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330144A (en) * | 2017-05-26 | 2017-11-07 | 昆明理工大学 | A kind of mixing proportion design method of the high tenacity cement base engineered composite material based on even test and ACE non parametric regressions |
| CN107391804A (en) * | 2017-06-27 | 2017-11-24 | 广东省建筑设计研究院 | Aseismic Behavior of Tall optimization method based on comprehensive cost method |
| CN110619187A (en) * | 2019-09-25 | 2019-12-27 | 三峡大学 | Concrete dam construction scheme and resource conflict detection and adjustment method |
| AU2020101453A4 (en) * | 2020-07-23 | 2020-08-27 | China Communications Construction Co., Ltd. | An Intelligent Optimization Method of Durable Concrete Mix Proportion Based on Data mining |
| CN113673125A (en) * | 2021-07-16 | 2021-11-19 | 华南理工大学 | Design method of connecting piece for assembled anti-collision guardrail |
| CN116050670A (en) * | 2023-03-31 | 2023-05-02 | 河北工业大学 | Road maintenance decision method and system based on data driving |
-
2023
- 2023-11-02 CN CN202311446632.6A patent/CN117162263B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330144A (en) * | 2017-05-26 | 2017-11-07 | 昆明理工大学 | A kind of mixing proportion design method of the high tenacity cement base engineered composite material based on even test and ACE non parametric regressions |
| CN107391804A (en) * | 2017-06-27 | 2017-11-24 | 广东省建筑设计研究院 | Aseismic Behavior of Tall optimization method based on comprehensive cost method |
| CN110619187A (en) * | 2019-09-25 | 2019-12-27 | 三峡大学 | Concrete dam construction scheme and resource conflict detection and adjustment method |
| AU2020101453A4 (en) * | 2020-07-23 | 2020-08-27 | China Communications Construction Co., Ltd. | An Intelligent Optimization Method of Durable Concrete Mix Proportion Based on Data mining |
| CN113673125A (en) * | 2021-07-16 | 2021-11-19 | 华南理工大学 | Design method of connecting piece for assembled anti-collision guardrail |
| CN116050670A (en) * | 2023-03-31 | 2023-05-02 | 河北工业大学 | Road maintenance decision method and system based on data driving |
Non-Patent Citations (1)
| Title |
|---|
| 混凝土配合比的优化设计;高云莉, 何煦;吉林建筑工程学院学报(第01期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117162263A (en) | 2023-12-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Malherbe et al. | Global optimization of Lipschitz functions | |
| Gandomi et al. | A new multi-gene genetic programming approach to nonlinear system modeling. Part I: materials and structural engineering problems | |
| Qian et al. | On constrained boolean pareto optimization | |
| Qian et al. | Selection hyper-heuristics can provably be helpful in evolutionary multi-objective optimization | |
| Mohammadi Bayazidi et al. | Multigene genetic programming for estimation of elastic modulus of concrete | |
| WO2002052365A2 (en) | Model predictive control (mpc) system using doe based model | |
| Shaqadan | Prediction of concrete mix strength using random forest model | |
| Fang et al. | Strength evaluation of granite block samples with different predictive models | |
| CN113312846B (en) | Intelligent detection method and system based on mixed technological process | |
| Yagiz et al. | Application of differential evolution algorithm and comparing its performance with literature to predict rock brittleness for excavatability | |
| Kadziński et al. | Multiple criteria ranking and choice with all compatible minimal cover sets of decision rules | |
| US20240062072A1 (en) | Federated learning system and federated learning method | |
| Vermetten et al. | Towards dynamic algorithm selection for numerical black-box optimization: investigating BBOB as a use case | |
| CN117162263B (en) | Method and system for optimizing concrete production process | |
| WO2021108603A1 (en) | Resolution preserving methodology to generate continuous log scale reservoir permeability profile from petrographic thin section images | |
| Tinoco et al. | A data-driven approach for qu prediction of laboratory soil-cement mixtures | |
| Yuan et al. | A hybrid approach to parameter tuning in genetic algorithms | |
| Jankovic et al. | Trajectory-based algorithm selection with warm-starting | |
| CN112185486B (en) | Cement-emulsified asphalt mixture shrinkage behavior prediction method based on deep learning | |
| CN115879829B (en) | Review expert screening method applied to platform innovation capability audit | |
| Ombach | A short introduction to stochastic optimization | |
| Tinoco et al. | Jet grouting mechanicals properties prediction using data mining techniques | |
| Khodaparasti et al. | Prediction of the concrete compressive strength using improved random forest algorithm | |
| Alzubi et al. | Parametric assessment of concrete constituent materials using machine learning techniques | |
| Abdi et al. | Elastic modulus estimation of weak rock samples using random forest technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |