CN117973947B - Standardized acceptance checking method and system for power distribution network engineering construction process - Google Patents
Standardized acceptance checking method and system for power distribution network engineering construction process Download PDFInfo
- Publication number
- CN117973947B CN117973947B CN202410381868.4A CN202410381868A CN117973947B CN 117973947 B CN117973947 B CN 117973947B CN 202410381868 A CN202410381868 A CN 202410381868A CN 117973947 B CN117973947 B CN 117973947B
- Authority
- CN
- China
- Prior art keywords
- construction
- scheme
- data
- acceptance
- representing
- 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
- 238000010276 construction Methods 0.000 title claims abstract description 286
- 238000000034 method Methods 0.000 title claims abstract description 138
- 230000008569 process Effects 0.000 title claims abstract description 105
- 238000004088 simulation Methods 0.000 claims abstract description 24
- 230000000694 effects Effects 0.000 claims abstract description 17
- 238000007781 pre-processing Methods 0.000 claims abstract description 13
- 238000012549 training Methods 0.000 claims description 36
- 238000004364 calculation method Methods 0.000 claims description 33
- 238000012544 monitoring process Methods 0.000 claims description 27
- 238000011156 evaluation Methods 0.000 claims description 20
- 230000006870 function Effects 0.000 claims description 17
- 238000013441 quality evaluation Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 14
- 238000000137 annealing Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 13
- 238000012795 verification Methods 0.000 claims description 12
- 230000000875 corresponding effect Effects 0.000 claims description 10
- 238000010586 diagram Methods 0.000 claims description 10
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 9
- 230000008030 elimination Effects 0.000 claims description 8
- 238000003379 elimination reaction Methods 0.000 claims description 8
- 238000013210 evaluation model Methods 0.000 claims description 8
- 238000013468 resource allocation Methods 0.000 claims description 8
- ORILYTVJVMAKLC-UHFFFAOYSA-N Adamantane Natural products C1C(C2)CC3CC1CC2C3 ORILYTVJVMAKLC-UHFFFAOYSA-N 0.000 claims description 7
- 230000001105 regulatory effect Effects 0.000 claims description 6
- 238000005516 engineering process Methods 0.000 claims description 4
- 239000000284 extract Substances 0.000 claims description 4
- 230000006872 improvement Effects 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 239000000463 material Substances 0.000 claims description 4
- 208000025174 PANDAS Diseases 0.000 claims description 3
- 208000021155 Paediatric autoimmune neuropsychiatric disorders associated with streptococcal infection Diseases 0.000 claims description 3
- 235000016496 Panda oleosa Nutrition 0.000 claims description 3
- 238000004458 analytical method Methods 0.000 claims description 3
- 230000002457 bidirectional effect Effects 0.000 claims description 3
- 230000001276 controlling effect Effects 0.000 claims description 3
- 238000011423 initialization method Methods 0.000 claims description 3
- 238000003058 natural language processing Methods 0.000 claims description 3
- 230000002596 correlated effect Effects 0.000 claims description 2
- 238000001914 filtration Methods 0.000 claims description 2
- 230000008520 organization Effects 0.000 claims description 2
- 240000000220 Panda oleosa Species 0.000 claims 1
- 230000002411 adverse Effects 0.000 abstract description 3
- 230000009286 beneficial effect Effects 0.000 abstract description 3
- 238000003908 quality control method Methods 0.000 abstract description 2
- 238000009499 grossing Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 240000004718 Panda Species 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses a standardized acceptance method and system for a power distribution network engineering construction process, which belong to the field of power distribution network engineering, and specifically comprise the following steps: (1) Collecting a large amount of power distribution network engineering construction data and preprocessing; (2) Modeling and organizing professional knowledge in the field of power distribution network engineering; (3) Generating an initial construction scheme and performing simulation adjustment on the initial construction scheme; the invention reduces the resource consumption and the cost expenditure, reduces the cost in the construction process, improves the efficiency of standardized acceptance of the construction process, can evaluate the feasibility and the robustness of the scheme more comprehensively, is beneficial to reducing the decision risk and improving the construction efficiency, effectively improves the accuracy and the comprehensiveness of acceptance, ensures that the acceptance process is more intelligent and automatic, reduces the influence of artificial subjective factors, is beneficial to improving the objectivity and the reliability of acceptance, effectively reduces the risk and the adverse effect in the construction process, and ensures the comprehensive quality control of the construction process.
Description
Technical Field
The invention relates to the field of power distribution network engineering, in particular to a standardized acceptance method and system for a power distribution network engineering construction process.
Background
In the field of power distribution network engineering, standardized acceptance of construction technology is an important link for ensuring engineering quality and safety. With the continuous growth of power supply and the continuous perfection of power grid systems in modern society, standard test collection of power distribution network engineering construction processes becomes more important. The distribution network is an important component in the power system and is responsible for transmitting electric energy from a high-voltage transmission line to each user side, so that the construction quality of the distribution network is directly related to the stability and safety of power supply. However, conventional construction process acceptance methods present a number of challenges. First, manual acceptance relies on experience and subjective judgment of the inspector, and is susceptible to personal factors, resulting in inconsistent acceptance results. Secondly, with the continuous expansion of the engineering scale and the improvement of the complexity of the power distribution network, the traditional acceptance method has difficulty in meeting the demands in terms of efficiency and accuracy. In addition, the traditional method often cannot fully utilize the existing construction data and expertise, and cannot realize comprehensive monitoring and management of the construction process.
The conventional standardized acceptance method and system resource consumption and cost expenditure of the power distribution network engineering construction process are high, the efficiency of standardized acceptance of the construction process is reduced, the feasibility and robustness of the scheme cannot be comprehensively evaluated, the influence of human subjective factors in the conventional standardized acceptance method and system acceptance process of the power distribution network engineering construction process is large, the objectivity and reliability of acceptance are not facilitated, and the risk and adverse influence in the construction process are increased; therefore, we propose a standardized acceptance method and system for the construction process of power distribution network engineering.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a standardized acceptance method and a standardized acceptance system for a power distribution network engineering construction process.
In order to achieve the above purpose, the present invention adopts the following technical scheme:
a standardized acceptance method for a power distribution network engineering construction process comprises the following specific steps:
(1) Collecting a large amount of power distribution network engineering construction data and preprocessing;
(2) Modeling and organizing professional knowledge in the field of power distribution network engineering;
(3) Generating an initial construction scheme and performing simulation adjustment on the initial construction scheme;
(4) Optimizing parameters in the construction scheme according to the simulation result;
(5) Monitoring the construction process in real time and dynamically regulating and managing construction resources;
(6) Monitoring and evaluating the construction process in real time and generating an acceptance report;
(7) Analyzing and summarizing the acceptance report and optimizing the automatic test acceptance flow.
As a further scheme of the invention, the construction data preprocessing of the step (1) comprises the following specific steps:
Step one: checking the structure, format and data type of the construction data, identifying the missing values in the data through Pandas, counting the number and proportion of the missing values in each group of data, and carrying out missing value position distribution analysis on each group of data;
Step two: if the missing value proportion is lower than a preset filling threshold, directly deleting the row or column containing the missing value, if the missing value proportion is higher than the preset filling threshold, processing the missing value through mean value filling, checking the processed data again, detecting and removing repeated records in the data, and storing the processed data as a new data set;
Step three: drawing a box diagram of the data set through a Seaborn library, respectively taking 25% quantile and 75% quantile of the data set as upper and lower quartiles of the box diagram, determining upper and lower edges according to the selected upper and lower quartiles, counting distribution conditions of each group of data in the data set in the box diagram, marking the data below the lower edge and above the upper edge as outliers, and processing the marked outliers through mean filling or direct elimination;
Step four: the processed construction data set is converted into standard normal distribution or a specific interval range through Z-score standardization, data from different data sources are integrated, repeated records are removed, the data in the different data sources are matched and correlated, then smoothing processing is carried out on the data through a moving average method, and frequency domain filtering is adopted to reduce noise of each group of data.
As a further scheme of the invention, the mean filling specific calculation formula in the second step is as follows:
in the/> Representing the mean value of the data where the missing value is located; /(I)Representing known data; /(I)Representing the amount of known data;
The specific calculation formula of the Z-score standardization is as follows:
in the/> Represents a normalized value; /(I)Representing the raw data; /(I)Represents the mean of the raw data; /(I)Represents standard deviation of the original data;
The specific calculation formula of the sliding average method is as follows:
in the/> Representative time/>Is a running average of (2); /(I)Representative time/>Is a piece of data from a database.
As a further aspect of the present invention, the specific steps of the expert knowledge modeling organization in the step (2) are as follows:
Step 1: collecting various pieces of expertise in the power distribution network engineering field, removing repeated and useless information in each collected piece of expertise, classifying the tidied expertise according to the content and the subject of the knowledge, and establishing a classification system of the knowledge according to the classification result;
Step 2: determining a hierarchical structure and an association relation among groups of categories, determining corresponding keywords or labels for each group of categories, identifying professional terms and entity names in each group of professional knowledge through a natural language processing technology, and extracting the relation among entities;
Step 3: determining entity types, attributes and relations of construction knowledge maps, constructing the construction knowledge maps by using a map database or a knowledge map tool according to knowledge modeling results, establishing association relations among entity nodes, correcting and optimizing the construction knowledge maps by expert auditing, and applying the constructed knowledge maps to actual power distribution network engineering.
As a further aspect of the present invention, the specific steps of generating the initial construction plan in the step (3) are as follows:
Step I: determining the structure and content of an initial scheme according to the existing construction standard and information in a construction knowledge graph, randomly generating the initial construction scheme, evaluating the generated initial construction scheme, calculating the quality evaluation index of the scheme, and setting the initial temperature Termination temperature/>Annealing Rate/>；
Step II: disturbance is carried out on an initial construction scheme through a local search strategy so as to generate a group of new construction schemes, quality evaluation is carried out on the generated new schemes, evaluation indexes are calculated, energy difference between the new schemes and the initial schemes is calculated, and then the energy difference is used for carrying out quality evaluation on the generated new schemesAnd the current temperature calculates the probability of acceptance/>；
Step III: randomly determining whether to accept the new scheme according to the acceptance probability, ifOr (b)Receiving a new construction scheme, otherwise, receiving the new scheme with preset probability, updating the current scheme to be the received new scheme or keeping the current scheme according to the random decision result, and updating the current temperature;
Step IV: repeating the generating and selecting steps to continuously update the iterative construction scheme until the current temperature reaches And stopping iteration, outputting a scheme with the minimum energy in the annealing process as an optimal construction scheme, feeding back the scheme to constructors for checking and adjusting, collecting adjustment information, and selectively updating the construction knowledge graph according to the adjustment information.
As a further scheme of the invention, the specific calculation formula of the quality evaluation index in the step I is as follows:
in the/> Representing the cost of the solution; Representing material costs; /(I) Representing labor costs; /(I)Representing equipment costs;
the specific calculation formula of the energy difference in the step II is as follows:
in the/> Representing an energy difference; /(I)Representing the cost required for the new construction scheme; /(I)Representing the cost required by the current construction;
the specific calculation formula of the acceptance probability in the step II is as follows:
in the/> Representing the current temperature parameter; /(I)A bottom representing natural logarithm;
and III, updating a specific calculation formula of the temperature:
in the/> Representing a new temperature parameter; /(I)Representing the annealing rate.
The standardized acceptance system for the power distribution network engineering construction process comprises a construction acceptance platform, a collection processing module, a map construction module, a scheme generation module, a simulation optimization module, a resource allocation module, a monitoring feedback module and a process acceptance module;
The construction acceptance platform is used for engineering constructors to check and adjust construction schemes and monitor implementation and acceptance of construction processes in real time;
the collection processing module is used for collecting and preprocessing a large amount of power distribution network engineering construction data;
The map construction module is used for constructing a corresponding knowledge map according to professional knowledge in the field of power distribution network engineering;
The scheme generating module is used for carrying out iterative optimization according to the existing data so as to generate an initial construction scheme;
the simulation optimization module is used for simulating the generated initial scheme and adjusting and improving according to a simulation result;
the resource allocation module is used for dynamically regulating and controlling the resource utilization in the construction process;
The monitoring feedback module is used for monitoring the construction process in real time and feeding back monitoring data to the construction acceptance platform;
The process acceptance module is used for monitoring and evaluating the construction process in real time and generating an acceptance report.
As a further scheme of the invention, the specific steps of the initial scheme adjustment and improvement of the simulation optimization module are as follows:
step ①: the simulation optimization module receives the generated initial construction scheme and the current construction state, constructs a group of exploration trees based on the initial construction scheme, and takes the current construction state as a root node in the exploration trees;
Step ②: expanding the root node according to the existing construction standard and the safety knowledge graph, generating various actions or strategies which can be adopted in the current construction state, simultaneously adding the generated actions and strategies as child nodes under the root node to expand the exploration tree, and then selecting the child node with the highest confidence upper bound through the UCB selection strategy;
Step ③: simulating a construction process based on the selected sub-nodes, generating a construction path, and evaluating the simulated construction path according to construction standards and a safety knowledge graph to acquire the construction effect and feasibility of the construction path;
step ④: updating the information of the current node according to the evaluation result, backtracking the node information to the root node, updating the information of each father node on the path, and repeating the steps of selecting, expanding, simulating and backtracking until the designated iteration times are reached;
Step ⑤: and collecting the construction effect and feasibility of each group of simulated construction paths, selecting the construction path with the best comprehensive effect as a final scheme according to the evaluation result, adjusting the initial construction scheme based on the scheme, and simultaneously monitoring the construction state in real time and updating scheme information.
As a further scheme of the present invention, the specific calculation formula of the UCB selection strategy is as follows:
in the/> Representing node/>Average benefit of (2); /(I)Representing the total number of simulations; /(I)Representing node/>Access times of (2); /(I)Represents any constant for the degree of balance exploration and utilization.
As a further scheme of the invention, the dynamic regulation and control specific steps of the resource allocation module are as follows:
The first step: creating a first linked list L1 and a second linked list L2, initializing two groups of pointers to point to the first linked list L1 and the second linked list L2 respectively, and simultaneously monitoring access conditions to resources in the construction process in real time;
And a second step of: checking the state of the data item in the cache, updating the state of the data item in the cache according to the access condition of the data item, if the data item exists in the cache, moving the data item into L1 or L2 according to the access frequency of the data item, and if the data item is not in the cache, determining whether the data item needs to be added into the cache according to a replacement strategy;
And a third step of: according to the reallocated cache space, updating the state of resources in the cache, periodically checking the capacity of the cache, dynamically adjusting the capacity of the cache according to the current use condition of the cache and the data access mode, if the cache exceeds the capacity limit, executing cache elimination operation according to the LRU and MRU principles, and deleting data meeting the elimination requirement to release the cache space.
As a further aspect of the present invention, the linked list L1 is used to store construction data with high call frequency. The linked list L2 is used for storing construction data with low calling frequency.
As a further scheme of the invention, the process acceptance module monitors and evaluates the specific steps as follows:
Step 1: the process acceptance module collects and preprocesses data in the power distribution network engineering construction process through a safety knowledge graph, the existing construction process standard and a historical construction scheme acceptance report, and extracts characteristic information of the construction process data through characteristic engineering;
Step 2: based on PyTorch libraries, a checking and accepting evaluation model is formed through a plurality of groups of bidirectional GRU layers, model parameters are set through a random initialization method, collected characteristic data are divided into a training set and a testing set, and the training set is divided into a plurality of groups of small-batch data;
Step 3: inputting a plurality of groups of training data into an acceptance assessment model in batches, calculating the predicted output of the model to the training data through a forward propagation algorithm, calculating the difference between the predicted output of the model and a real label based on a cross entropy loss function, and calculating the gradient of the loss function to model parameters through a backward propagation algorithm;
Step 4: cutting the calculated gradient, updating parameters of the model by using an Adam optimizer according to the cut gradient, evaluating the performance of the trained model by using a verification set after each training period is finished, and calculating a loss function and an evaluation index of the model on the verification set;
Step 5: adjusting the super parameters of the acceptance assessment model according to the performance on the verification set, then repeatedly training the model until the performance of the model is not improved or starts to deteriorate, otherwise, continuing training the model until the preset training times are reached, stopping, and storing the trained model information after each training time;
step 6: collecting and preprocessing data in the actual construction process, taking the preprocessed construction data as input, inputting the input data into a trained acceptance assessment model for inference, outputting a corresponding acceptance result by the model for each group of input samples, and then outputting the acceptance result inferred by the model into an acceptance report or a database for reservation.
As a further scheme of the invention, the specific calculation formula of the cross entropy loss function in the step 3 is as follows:
in the/> Representing the number of samples; /(I)Represents the/>Actual labels of the individual samples; /(I)Representative model pair/>Prediction probabilities of the individual samples;
the Adam optimizer in step 4 has the following specific calculation formula:
in the/> Representing model parameters; /(I)Representing a learning rate; /(I)Representing the loss function with respect to the parameter/>Is a gradient of (2); /(I)And/>Represents an exponential decay rate; /(I)And/>Representing a moving average of the first moment estimate and the second moment estimate, respectively; /(I)Representing a small constant added for numerical stability;
The specific calculation formula of the evaluation index in the step 4 is as follows:
in the/> Representing the number of real cases; /(I)Representing the number of true negative examples; /(I)Representing the number of false positive cases; /(I)Representing the number of false negatives; /(I)Representing the accuracy; Representing the accuracy; /(I) Representing recall rate; /(I)Representing the harmonic mean of the precision and recall.
Compared with the prior art, the invention has the beneficial effects that:
1. The standardized acceptance method for the power distribution network engineering construction process comprises the steps of determining the structure and the content of an initial scheme according to the existing construction standard and information in a construction knowledge graph, randomly generating the initial construction scheme, calculating the quality evaluation index of the scheme, then disturbing the initial construction scheme through a local search strategy to generate a set of new construction scheme, carrying out quality evaluation on the generated new scheme, calculating the evaluation index, calculating the energy difference between the new scheme and the initial scheme, updating the new scheme accepted by the current scheme according to a random decision result or keeping the current scheme, repeatedly updating the initial construction scheme through an annealing algorithm until the initial construction scheme reaches a termination temperature, constructing a set of exploratory tree based on the initial construction scheme, taking the current construction state as a root node in the exploratory tree, expanding the root node according to the existing construction standard and a safety knowledge graph, selecting a set of sub-nodes to simulate the construction process, generating a construction path, evaluating the new construction path according to the construction standard and the safety knowledge graph, repeatedly carrying out the steps of selection, expansion, simulation and backtracking until the designated iteration number is reached, stopping updating the current scheme to accept the new scheme or keeping the current scheme, constructing a set of exploratory tree is constructed on the basis of the initial construction scheme, the fact that the initial construction state is used as a root node in the exploratory tree, the construction process is expanded, the construction cost is reduced, the practical evaluation is improved, the construction cost is reduced, the construction cost is improved, and the construction cost is better estimated and calculated.
2. The standardized acceptance system for the power distribution network engineering construction process collects and preprocesses data in the power distribution network engineering construction process, extracts characteristic information of the construction process data through characteristic engineering, builds an acceptance assessment model based on PyTorch libraries, divides the collected characteristic data into a training set and a testing set, divides the training set into a plurality of groups of small batches of data, inputs the plurality of groups of training data into the acceptance assessment model in batches, calculates predicted output of the model on the training data through a forward propagation algorithm, calculates a gap between the predicted output of the model and a real label based on a cross entropy loss function, calculates gradients of model parameters through a back propagation algorithm, cuts the calculated gradients, updates the parameters of the model according to the cut gradients by using an Adam optimizer, after each training period is finished, evaluating the performance of the trained model by using a verification set, calculating a loss function and an evaluation index of the model on the verification set, adjusting the hyper-parameters of the acceptance evaluation model according to the performance on the verification set, then repeatedly training the model until the performance of the model is not improved or starts to deteriorate, otherwise, continuing training the model until the preset training times are reached, stopping, storing the trained model information after each training, collecting and preprocessing the data in the actual construction process, taking the preprocessed construction data as input, inputting the preprocessed construction data into the trained acceptance evaluation model for inference, outputting the corresponding acceptance result of the model inference to an acceptance report or database for reservation by the model, effectively improving the accuracy and the comprehensiveness of acceptance, the inspection and acceptance process is more intelligent and automatic, the influence of human subjective factors is reduced, the objectivity and reliability of inspection and acceptance are improved, the risk and adverse effect in the construction process are effectively reduced, and the comprehensive quality control of the construction process is ensured.
Drawings
The accompanying drawings are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate the invention and together with the embodiments of the invention, serve to explain the invention.
Fig. 1 is a flow chart of a standardized acceptance method of a power distribution network engineering construction process;
FIG. 2 is a system block diagram of a standard test collecting system for a power distribution network engineering construction process, which is provided by the invention;
fig. 3 is a flowchart of generating an initial scheme of a standardized acceptance method of a power distribution network engineering construction process.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments.
Embodiment 1, referring to fig. 1 and 3, the embodiment discloses a standardized acceptance method for a power distribution network engineering construction process, which specifically comprises the following steps:
and collecting a large amount of power distribution network engineering construction data and preprocessing.
Specifically, checking the structure, format and data type of construction data, identifying the missing values in the data through Pandas, counting the number and proportion of the missing values in each group of data, carrying out missing value position distribution analysis on each group of data, directly deleting the row or column containing the missing values if the missing value proportion is lower than a preset filling threshold, processing the missing values through mean filling if the missing value proportion is higher than the preset filling threshold, checking the processed data again, detecting and removing repeated records in the data, storing the processed data as a new data set, drawing a box diagram of the data set through a Seaborn library, respectively taking the 25% quantile and 75% quantile of the data set as upper and lower quartiles of the box diagram, determining the upper and lower edges according to the selected upper and lower quartiles, counting the distribution condition of each group of data in the box diagram, marking the data below the lower edge and above the upper edge as abnormal values, carrying out filling or directly removing the abnormal values marked through mean filling or removing the abnormal values, carrying out Z-score conversion on the processed data, carrying out the data from the data set to be integrated with the standard of different types, smoothing the data, carrying out the same source-to the data, and carrying out smoothing processing, and carrying out the same-source-smoothing processing on the data.
It should be further noted that the specific calculation formula of the mean filling is as follows:
in the/> Representing the mean value of the data where the missing value is located; /(I)Representing known data; /(I)Representing the amount of known data;
the specific calculation formula for Z-score standardization is as follows:
in the/> Represents a normalized value; /(I)Representing the raw data; /(I)Represents the mean of the raw data; /(I)Represents standard deviation of the original data;
The specific calculation formula of the sliding average method is as follows:
in the/> Representative time/>Is a running average of (2); /(I)Representative time/>Is a piece of data from a database.
Modeling and organizing the professional knowledge in the field of power distribution network engineering.
Specifically, various specialized knowledge in the field of power distribution network engineering is collected, repeated and useless information in each collected specialized knowledge is removed, the sorted specialized knowledge is classified according to the content and the subject of the knowledge, a classification system of the knowledge is established according to classification results, a hierarchical structure and an association relation between each group of classes are determined, corresponding keywords or labels are determined for each group of classes, the specialized terms and entity names in each group of specialized knowledge are identified through natural language processing technology, the relation between entities is extracted, the entity type, attribute and relation of a construction knowledge map are determined, the construction knowledge map is constructed by utilizing a graph database or a knowledge map tool according to knowledge modeling results, the association relation between entity nodes is established, the construction knowledge map is corrected and optimized through experts, and the constructed knowledge map is applied to actual power distribution network engineering.
An initial construction plan is generated and simulated adjustments are made thereto.
Specifically, referring to fig. 3, the structure and content of an initial scheme are determined according to the existing construction standard and information in a construction knowledge graph, and an initial construction scheme is randomly generated, the generated initial construction scheme is evaluated, a quality evaluation index of the scheme is calculated, and then an initial temperature is setTermination temperature/>Annealing Rate/>Disturbance is carried out on an initial construction scheme through a local search strategy so as to generate a group of new construction schemes, quality evaluation is carried out on the generated new schemes, evaluation indexes are calculated, energy difference between the new schemes and the initial schemes is calculated, and then the energy difference/>, according to the energy difference, is carried outAnd the current temperature calculates the probability of acceptance/>Randomly determining whether to accept the new scheme according to the acceptance probability, if/>Or (b)Receiving new construction scheme, otherwise, receiving new scheme with preset probability, updating current scheme to be the new scheme or keeping current scheme according to random decision result, updating current temperature, repeating generation and selection steps to continuously update iterative construction scheme until current temperature reaches/>And stopping iteration, outputting a scheme with the minimum energy in the annealing process as an optimal construction scheme, feeding back the scheme to constructors for checking and adjusting, collecting adjustment information, and selectively updating the construction knowledge graph according to the adjustment information.
In this embodiment, the specific calculation formula of the quality evaluation index is as follows:
in the/> Representing the cost of the solution; /(I)Representing material costs; /(I)Representing labor costs; /(I)Representing equipment costs;
the specific calculation formula of the energy difference is as follows:
in the/> Representing an energy difference; /(I)Representing the cost required for the new construction scheme; /(I)Representing the cost required by the current construction;
the specific calculation formula of the acceptance probability is as follows:
in the/> Representing the current temperature parameter; /(I)A bottom representing natural logarithm;
the specific calculation formula of the temperature update is as follows:
in the/> Representing a new temperature parameter; /(I)Representing the annealing rate.
And optimizing parameters in the construction scheme according to the simulation result.
And monitoring the construction process in real time and dynamically regulating and managing construction resources.
And monitoring and evaluating the construction process in real time and generating an acceptance report.
Analyzing and summarizing the acceptance report and optimizing the automatic test acceptance flow.
Embodiment 2, referring to fig. 2, the embodiment discloses a standardized acceptance system for a power distribution network engineering construction process, which comprises a construction acceptance platform, a collection processing module, a map construction module, a scheme generation module, a simulation optimization module, a resource allocation module, a monitoring feedback module and a process acceptance module.
The construction acceptance platform is used for engineering constructors to check and adjust construction schemes and monitor implementation and acceptance of construction processes in real time; the collection processing module is used for collecting and preprocessing a large amount of power distribution network engineering construction data; the map construction module is used for constructing a corresponding knowledge map according to the professional knowledge in the power distribution network engineering field; the scheme generation module is used for carrying out iterative optimization according to the existing data so as to generate an initial construction scheme; the simulation optimizing module is used for simulating the generated initial scheme and adjusting and improving according to the simulation result.
Specifically, the simulation optimization module receives the generated initial construction scheme and the current construction state, constructs a group of exploration trees based on the initial construction scheme, takes the current construction state as a root node in the exploration tree, expands the root node according to the existing construction standard and safety knowledge graph, generates various actions or strategies which can be adopted under the current construction state, simultaneously adds the generated actions and strategies as child nodes under the root node to expand the exploration tree, then selects the child node with the highest confidence upper bound through UCB selection strategy, simulates the construction process based on the selected child node, generates a construction path, evaluates the simulated construction path according to the construction standard and the safety knowledge graph to obtain the construction effect and feasibility of the construction path, updates the information of the current node according to the evaluation result, and backtracks the node information to the root node, repeatedly performs the steps of selection, expansion, simulation and backtracking until the designated iteration times are reached, collects the construction effect and feasibility of each group of the simulated construction path, has the best construction effect and the best construction effect, and the optimal construction effect is adjusted based on the comprehensive scheme, and the construction effect is adjusted based on the comprehensive scheme.
In this embodiment, the specific calculation formula of the UCB selection policy is as follows:
in the/> Representing node/>Average benefit of (2); /(I)Representing the total number of simulations; /(I)Representing node/>Access times of (2); /(I)Represents any constant for the degree of balance exploration and utilization.
The resource allocation module is used for dynamically regulating and controlling the resource utilization in the construction process.
Specifically, a first linked list L1 and a second linked list L2 are created, two groups of pointers are initialized to point to the first linked list L1 and the second linked list L2 respectively, access conditions to resources in the construction process are monitored in real time, states of data items in a cache are checked, the states of the data items in the cache are updated according to the access conditions of the data items, if the data items are already in the cache, the data items are moved to the L1 or the L2 according to the access frequency of the data items, if the data items are not in the cache, whether the data items need to be added into the cache is determined according to a replacement strategy, the states of resources in the cache are updated according to the reallocated cache space, the cache capacity is checked regularly, the cache capacity is adjusted dynamically according to the current use condition and the data access mode of the cache, if the cache exceeds capacity limit, cache elimination operation is executed according to LRU and MRU principles, and data meeting elimination requirements are deleted to release the cache space.
It should be further noted that the linked list L1 is used to store construction data with high call frequency. The linked list L2 is used for storing construction data with low calling frequency.
The monitoring feedback module is used for monitoring the construction process in real time and feeding back monitoring data to the construction acceptance platform; the process acceptance module is used for monitoring and evaluating the construction process in real time and generating an acceptance report.
Specifically, the process acceptance module collects and preprocesses data in the construction process of the power distribution network engineering through a safety knowledge graph, the existing construction process standard and a historical construction scheme acceptance report, extracts characteristic information of the construction process data through characteristic engineering, sets an acceptance evaluation model through a plurality of groups of bidirectional GRU layer, sets model parameters through a random initialization method, divides the collected characteristic data into a training set and a test set, divides the training set into a plurality of groups of small batch data, inputs a plurality of groups of training data into the acceptance evaluation model in batches, calculates the prediction output of the model for the training data through a forward propagation algorithm, calculates the difference between the model prediction output and a real label based on a cross entropy loss function, calculates the gradient of a loss function model parameter through a reverse propagation algorithm, cutting the calculated gradient, updating parameters of the model by using an Adam optimizer according to the cut gradient, evaluating the performance of the trained model by using a verification set after each training period is finished, calculating a loss function and an evaluation index of the model on the verification set, adjusting the hyper-parameters of the acceptance evaluation model according to the performance on the verification set, then repeatedly training the model until the performance of the model is not improved or starts to deteriorate, stopping training until the model is continuously trained until the preset training times are reached, storing model information after the training is finished each time, collecting and preprocessing data in the actual construction process, inputting the preprocessed construction data into the trained acceptance evaluation model for inference, outputting corresponding acceptance results by the model for each group of input samples, and outputting the acceptance result inferred by the model to an acceptance report or a database for reservation.
In this embodiment, the specific calculation formula of the cross entropy loss function is as follows:
in the/> Representing the number of samples; /(I)Represents the/>Actual labels of the individual samples; /(I)Representative model pair/>Prediction probabilities of the individual samples;
the Adam optimizer has the following specific calculation formula:
in the/> Representing model parameters; /(I)Representing a learning rate; /(I)Representing the loss function with respect to the parameter/>Is a gradient of (2); /(I)And/>Represents an exponential decay rate; /(I)And/>Representing a moving average of the first moment estimate and the second moment estimate, respectively; /(I)Representing a small constant added for numerical stability;
The specific calculation formula of the evaluation index is as follows:
in the/> Representing the number of real cases; /(I)Representing the number of true negative examples; /(I)Representing the number of false positive cases; /(I)Representing the number of false negatives; /(I)Representing the accuracy; Representing the accuracy; /(I) Representing recall rate; /(I)Representing the harmonic mean of the precision and recall. /(I)
Claims (6)
1. The standardized acceptance method for the power distribution network engineering construction process is characterized by comprising the following specific steps of:
(1) Collecting a large amount of power distribution network engineering construction data and preprocessing;
(2) Modeling and organizing professional knowledge in the field of power distribution network engineering;
(3) Generating an initial construction scheme and performing simulation adjustment on the initial construction scheme;
(4) Optimizing parameters in the construction scheme according to the simulation result;
(5) Monitoring the construction process in real time and dynamically regulating and managing construction resources;
(6) Monitoring and evaluating the construction process in real time and generating an acceptance report;
(7) Analyzing and summarizing the acceptance report and optimizing an automatic test acceptance flow;
the specific steps of the expert knowledge modeling organization are as follows:
Step 1: collecting various pieces of expertise in the power distribution network engineering field, removing repeated and useless information in each collected piece of expertise, classifying the tidied expertise according to the content and the subject of the knowledge, and establishing a classification system of the knowledge according to the classification result;
Step 2: determining a hierarchical structure and an association relation among groups of categories, determining corresponding keywords or labels for each group of categories, identifying professional terms and entity names in each group of professional knowledge through a natural language processing technology, and extracting the relation among entities;
Step 3: determining entity types, attributes and relations of construction knowledge maps, constructing the construction knowledge maps by using a map database or a knowledge map tool according to knowledge modeling results, establishing association relations among entity nodes, correcting and optimizing the construction knowledge maps by expert auditing, and applying the constructed knowledge maps to actual power distribution network engineering;
the specific steps of the initial construction scheme generation are as follows:
Step I: determining the structure and content of an initial scheme according to the existing construction standard and information in a construction knowledge graph, randomly generating the initial construction scheme, evaluating the generated initial construction scheme, calculating the quality evaluation index of the scheme, and setting the initial temperature Termination temperature/>Annealing Rate/>；
Step II: disturbance is carried out on an initial construction scheme through a local search strategy so as to generate a group of new construction schemes, quality evaluation is carried out on the generated new schemes, evaluation indexes are calculated, energy difference between the new schemes and the initial schemes is calculated, and acceptance probability is calculated according to the energy difference and the current temperature；
Step III: randomly determining whether to accept the new scheme according to the acceptance probability, ifOr/>Receiving a new construction scheme, otherwise, receiving the new scheme with preset probability, updating the current scheme to be the received new scheme or keeping the current scheme according to the random decision result, and updating the current temperature;
Step IV: repeating the generating and selecting steps to continuously update the iterative construction scheme until the current temperature reaches, stopping iteration, outputting the scheme with the minimum energy in the annealing process as an optimal construction scheme, feeding back the scheme to constructors for checking and adjusting, collecting adjustment information at the same time, and selectively updating the construction knowledge graph according to the adjustment information;
the specific calculation formula of the quality evaluation index in the step I is as follows:
In the method, in the process of the invention, Representing the cost of the solution; /(I)Representing material costs; /(I)Representing labor costs; representing equipment costs;
the specific calculation formula of the energy difference in the step II is as follows:
In the method, in the process of the invention, Representing an energy difference; /(I)Representing the cost required for the new construction scheme; /(I)Representing the cost required by the current construction;
the specific calculation formula of the acceptance probability in the step II is as follows:
In the method, in the process of the invention, Representing the current temperature parameter; /(I)A bottom representing natural logarithm;
and III, updating a specific calculation formula of the temperature:
In the method, in the process of the invention, Representing a new temperature parameter; /(I)Represents the annealing rate;
the specific steps of the initial construction scheme adjustment and improvement are as follows:
step ①: the simulation optimization module receives the generated initial construction scheme and the current construction state, constructs a group of exploration trees based on the initial construction scheme, and takes the current construction state as a root node in the exploration trees;
Step ②: expanding the root node according to the existing construction standard and the safety knowledge graph, generating various actions or strategies which can be adopted in the current construction state, simultaneously adding the generated actions and strategies as child nodes under the root node to expand the exploration tree, and then selecting the child node with the highest confidence upper bound through the UCB selection strategy;
Step ③: simulating a construction process based on the selected sub-nodes, generating a construction path, and evaluating the simulated construction path according to construction standards and a safety knowledge graph to acquire the construction effect and feasibility of the construction path;
step ④: updating the information of the current node according to the evaluation result, backtracking the node information to the root node, updating the information of each father node on the path, and repeating the steps of selecting, expanding, simulating and backtracking until the designated iteration times are reached;
Step ⑤: and collecting the construction effect and feasibility of each group of simulated construction paths, selecting the construction path with the best comprehensive effect as a final scheme according to the evaluation result, adjusting the initial construction scheme based on the scheme, and simultaneously monitoring the construction state in real time and updating scheme information.
2. The standardized inspection and acceptance method for power distribution network engineering construction process according to claim 1, wherein the construction data preprocessing in the step (1) specifically comprises the following steps:
Step one: checking the structure, format and data type of the construction data, identifying the missing values in the data through Pandas, counting the number and proportion of the missing values in each group of data, and carrying out missing value position distribution analysis on each group of data;
Step two: if the missing value proportion is lower than a preset filling threshold, directly deleting the row or column containing the missing value, if the missing value proportion is higher than the preset filling threshold, processing the missing value through mean value filling, checking the processed data again, detecting and removing repeated records in the data, and storing the processed data as a new data set;
Step three: drawing a box diagram of the data set through a Seaborn library, respectively taking 25% quantile and 75% quantile of the data set as upper and lower quartiles of the box diagram, determining upper and lower edges according to the selected upper and lower quartiles, counting distribution conditions of each group of data in the data set in the box diagram, marking the data below the lower edge and above the upper edge as outliers, and processing the marked outliers through mean filling or direct elimination;
step four: the processed construction data set is converted into standard normal distribution or a specific interval range through Z-score standardization, data from different data sources are integrated, repeated records are removed, the data in the different data sources are matched and correlated, then each group of data is smoothed through a moving average method, and frequency domain filtering is adopted to reduce noise of each group of data.
3. The standardized acceptance system for the power distribution network engineering construction process is characterized by comprising a construction acceptance platform, a collection processing module, a map construction module, a scheme generation module, a simulation optimization module, a resource allocation module, a monitoring feedback module and a process acceptance module;
The construction acceptance platform is used for engineering constructors to check and adjust construction schemes and monitor implementation and acceptance of construction processes in real time;
the collection processing module is used for collecting and preprocessing a large amount of power distribution network engineering construction data;
The map construction module is used for constructing a corresponding knowledge map according to professional knowledge in the field of power distribution network engineering;
The scheme generating module is used for carrying out iterative optimization according to the existing data so as to generate an initial construction scheme;
the specific steps of the initial construction scheme generation are as follows:
Step I: determining the structure and content of an initial scheme according to the existing construction standard and information in a construction knowledge graph, randomly generating the initial construction scheme, evaluating the generated initial construction scheme, calculating the quality evaluation index of the scheme, and setting the initial temperature Termination temperature/>Annealing Rate/>；
Step II: disturbance is carried out on an initial construction scheme through a local search strategy so as to generate a group of new construction schemes, quality evaluation is carried out on the generated new schemes, evaluation indexes are calculated, energy difference between the new schemes and the initial schemes is calculated, and then the energy difference is used for carrying out quality evaluation on the generated new schemesAnd the current temperature calculates the probability of acceptance/>；
Step III: randomly determining whether to accept the new scheme according to the acceptance probability, ifOr/>Receiving a new construction scheme, otherwise, receiving the new scheme with preset probability, updating the current scheme to be the received new scheme or keeping the current scheme according to the random decision result, and updating the current temperature;
Step IV: repeating the generating and selecting steps to continuously update the iterative construction scheme until the current temperature reaches When the construction method is used, iteration is stopped, then a scheme with the minimum energy in the annealing process is output as an optimal construction scheme, the scheme is fed back to constructors for checking and adjusting, adjusting information is collected, and the construction knowledge graph is selected and updated according to the adjusting information;
the specific calculation formula of the quality evaluation index in the step I is as follows:
In the method, in the process of the invention, Representing the cost of the solution; /(I)Representing material costs; /(I)Representing labor costs; representing equipment costs;
the specific calculation formula of the energy difference in the step II is as follows:
In the method, in the process of the invention, Representing an energy difference; /(I)Representing the cost required for the new construction scheme; /(I)Representing the cost required by the current construction;
the specific calculation formula of the acceptance probability in the step II is as follows:
In the method, in the process of the invention, Representing the current temperature parameter; /(I)A bottom representing natural logarithm;
and III, updating a specific calculation formula of the temperature:
In the method, in the process of the invention, Representing a new temperature parameter; /(I)Represents the annealing rate;
the simulation optimization module is used for simulating the generated initial scheme and adjusting and improving according to a simulation result;
The specific steps of the initial scheme adjustment and improvement are as follows:
step ①: the simulation optimization module receives the generated initial construction scheme and the current construction state, constructs a group of exploration trees based on the initial construction scheme, and takes the current construction state as a root node in the exploration trees;
Step ②: expanding the root node according to the existing construction standard and the safety knowledge graph, generating various actions or strategies which can be adopted in the current construction state, simultaneously adding the generated actions and strategies as child nodes under the root node to expand the exploration tree, and then selecting the child node with the highest confidence upper bound through the UCB selection strategy;
Step ③: simulating a construction process based on the selected sub-nodes, generating a construction path, and evaluating the simulated construction path according to construction standards and a safety knowledge graph to acquire the construction effect and feasibility of the construction path;
step ④: updating the information of the current node according to the evaluation result, backtracking the node information to the root node, updating the information of each father node on the path, and repeating the steps of selecting, expanding, simulating and backtracking until the designated iteration times are reached;
Step ⑤: collecting the construction effect and feasibility of each group of simulated construction paths, selecting the construction path with the best comprehensive effect as a final scheme according to the evaluation result, adjusting the initial construction scheme based on the scheme, and simultaneously monitoring the construction state in real time and updating scheme information;
the resource allocation module is used for dynamically regulating and controlling the resource utilization in the construction process;
The monitoring feedback module is used for monitoring the construction process in real time and feeding back monitoring data to the construction acceptance platform;
The process acceptance module is used for monitoring and evaluating the construction process in real time and generating an acceptance report.
4. A standardized inspection and acceptance system for power distribution network engineering construction process according to claim 3, wherein the dynamic regulation and control of the resource allocation module comprises the following specific steps:
The first step: creating a first linked list L1 and a second linked list L2, initializing two groups of pointers to point to the first linked list L1 and the second linked list L2 respectively, and simultaneously monitoring access conditions to resources in the construction process in real time;
And a second step of: checking the state of the data item in the cache, updating the state of the data item in the cache according to the access condition of the data item, if the data item exists in the cache, moving the data item into L1 or L2 according to the access frequency of the data item, and if the data item is not in the cache, determining whether the data item needs to be added into the cache according to a replacement strategy;
And a third step of: according to the reallocated cache space, updating the state of resources in the cache, periodically checking the capacity of the cache, dynamically adjusting the capacity of the cache according to the current use condition of the cache and the data access mode, if the cache exceeds the capacity limit, executing cache elimination operation according to the LRU and MRU principles, and deleting data meeting the elimination requirement to release the cache space.
5. The standardized acceptance system of a power distribution network engineering construction process according to claim 4, wherein the process acceptance module monitors and evaluates the following specific steps:
Step 1: the process acceptance module collects and preprocesses data in the power distribution network engineering construction process through a safety knowledge graph, the existing construction process standard and a historical construction scheme acceptance report, and extracts characteristic information of the construction process data through characteristic engineering;
Step 2: based on PyTorch libraries, a checking and accepting evaluation model is formed through a plurality of groups of bidirectional GRU layers, model parameters are set through a random initialization method, collected characteristic data are divided into a training set and a testing set, and the training set is divided into a plurality of groups of small-batch data;
Step 3: inputting a plurality of groups of training data into an acceptance assessment model in batches, calculating the predicted output of the model to the training data through a forward propagation algorithm, calculating the difference between the predicted output of the model and a real label based on a cross entropy loss function, and calculating the gradient of the loss function to model parameters through a backward propagation algorithm;
Step 4: cutting the calculated gradient, updating parameters of the model by using an Adam optimizer according to the cut gradient, evaluating the performance of the trained model by using a verification set after each training period is finished, and calculating a loss function and an evaluation index of the model on the verification set;
Step 5: adjusting the super parameters of the acceptance assessment model according to the performance on the verification set, then repeatedly training the model until the performance of the model is not improved or starts to deteriorate, otherwise, continuing training the model until the preset training times are reached, stopping, and storing the trained model information after each training time;
step 6: collecting and preprocessing data in the actual construction process, taking the preprocessed construction data as input, inputting the input data into a trained acceptance assessment model for inference, outputting a corresponding acceptance result by the model for each group of input samples, and then outputting the acceptance result inferred by the model into an acceptance report or a database for reservation.
6. The standardized acceptance system of a power distribution network engineering construction process according to claim 5, wherein the specific calculation formula of the cross entropy loss function in step 3 is as follows:
In the method, in the process of the invention, Representing the number of samples; /(I)Represents the/>Actual labels of the individual samples; /(I)Representative model pair/>Prediction probabilities of the individual samples;
the Adam optimizer in step 4 has the following specific calculation formula:
In the method, in the process of the invention, Representing model parameters; /(I)Representing a learning rate; /(I)Representing the loss function with respect to the parameter/>Is a gradient of (2); /(I)And/>Represents an exponential decay rate; /(I)And/>Representing a moving average of the first moment estimate and the second moment estimate, respectively; /(I)Representing a small constant added for numerical stability;
The specific calculation formula of the evaluation index in the step 4 is as follows:
In the method, in the process of the invention, Representing the number of real cases; /(I)Representing the number of true negative examples; /(I)Representing the number of false positive cases; /(I)Representing the number of false negatives; /(I)Representing the accuracy; /(I)Representing the accuracy; /(I)Representing recall rate; representing the harmonic mean of the precision and recall.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410381868.4A CN117973947B (en) | 2024-04-01 | 2024-04-01 | Standardized acceptance checking method and system for power distribution network engineering construction process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410381868.4A CN117973947B (en) | 2024-04-01 | 2024-04-01 | Standardized acceptance checking method and system for power distribution network engineering construction process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117973947A CN117973947A (en) | 2024-05-03 |
| CN117973947B true CN117973947B (en) | 2024-06-14 |
Family
ID=90864954
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410381868.4A Active CN117973947B (en) | 2024-04-01 | 2024-04-01 | Standardized acceptance checking method and system for power distribution network engineering construction process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117973947B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700192A (en) * | 2014-11-03 | 2015-06-10 | 国网浙江省电力公司嘉兴供电公司 | Aided intelligent management and control system for power transmission and transformation project and management and control method thereof |
| CN116882038A (en) * | 2023-09-08 | 2023-10-13 | 南通汤姆瑞斯工业智能科技有限公司 | Electromechanical construction method and system based on BIM technology |
| CN117371933A (en) * | 2023-10-08 | 2024-01-09 | 广州市科颐轩电子科技有限公司 | Intelligent laboratory management system based on Internet of things |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110258442B (en) * | 2019-05-31 | 2021-03-30 | 中交水运规划设计院有限公司 | Method and device for determining engineering construction process scheme of high-pile wharf |
| CN110598298A (en) * | 2019-09-04 | 2019-12-20 | 北京华科软科技有限公司 | Design and construction integrated visual management working platform based on BIM |
| CN113298435A (en) * | 2021-06-21 | 2021-08-24 | 中交第二航务工程局有限公司 | Intelligent construction scheme compiling method and system for building industry |
| CN113609548B (en) * | 2021-07-05 | 2023-10-24 | 中铁工程设计咨询集团有限公司 | Bridge span distribution method, device, equipment and readable storage medium |
| CN114638595B (en) * | 2022-04-11 | 2022-12-30 | 中国建筑第二工程局有限公司 | Complexity-optimized construction scheme compiling system and application method thereof |
| CN114496234B (en) * | 2022-04-18 | 2022-07-19 | 浙江大学 | Cognitive-atlas-based personalized diagnosis and treatment scheme recommendation system for general patients |
| CN115713495A (en) * | 2022-11-03 | 2023-02-24 | 国网四川岷江供电有限责任公司 | Electric power construction task acceptance method based on augmented reality |
| CN115982329A (en) * | 2022-12-27 | 2023-04-18 | 中交第二航务工程局有限公司 | Intelligent generation method and system for engineering construction scheme compilation basis |
| CN116522643A (en) * | 2023-04-28 | 2023-08-01 | 中国电力科学研究院有限公司 | Automatic construction method and system for power grid operation simulation scheme library |
| CN116757534B (en) * | 2023-06-15 | 2024-03-15 | 中国标准化研究院 | Intelligent refrigerator reliability analysis method based on neural training network |
| CN117391674A (en) * | 2023-11-02 | 2024-01-12 | 上海电机学院 | Reliability-based preventive maintenance optimization method and device for electrical equipment |
| CN117669176A (en) * | 2023-11-28 | 2024-03-08 | 国网辽宁省电力有限公司本溪供电公司 | Power distribution network reliability assessment method and device based on network simplification method |
| CN117473840B (en) * | 2023-12-26 | 2024-04-26 | 中交第四航务工程勘察设计院有限公司 | Simulation and optimization method and system based on construction process for sheet pile wharf |
-
2024
- 2024-04-01 CN CN202410381868.4A patent/CN117973947B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104700192A (en) * | 2014-11-03 | 2015-06-10 | 国网浙江省电力公司嘉兴供电公司 | Aided intelligent management and control system for power transmission and transformation project and management and control method thereof |
| CN116882038A (en) * | 2023-09-08 | 2023-10-13 | 南通汤姆瑞斯工业智能科技有限公司 | Electromechanical construction method and system based on BIM technology |
| CN117371933A (en) * | 2023-10-08 | 2024-01-09 | 广州市科颐轩电子科技有限公司 | Intelligent laboratory management system based on Internet of things |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117973947A (en) | 2024-05-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112987666B (en) | Power plant unit operation optimization regulation and control method and system | |
| CN111950585A (en) | XGboost-based underground comprehensive pipe gallery safety condition assessment method | |
| CN110826237B (en) | Wind power equipment reliability analysis method and device based on Bayesian belief network | |
| CN111126865B (en) | Technology maturity judging method and system based on technology big data | |
| CN110690701A (en) | Analysis method for influence factors of abnormal line loss | |
| CN112990500A (en) | Transformer area line loss analysis method and system based on improved weighted gray correlation analysis | |
| CN111860624A (en) | Power grid fault information classification method based on decision tree | |
| CN113780684A (en) | Intelligent building user energy consumption behavior prediction method based on LSTM neural network | |
| CN116933010A (en) | Load rate analysis and evaluation method and system based on multi-source data fusion and deep learning | |
| CN117371933A (en) | Intelligent laboratory management system based on Internet of things | |
| CN110059938B (en) | Power distribution network planning method based on association rule driving | |
| CN116128544A (en) | Active auditing method and system for electric power marketing abnormal business data | |
| CN116204779A (en) | Method, system and readable storage medium for judging operation state of energy storage salt cavern | |
| CN112836876B (en) | Power distribution network line load prediction method based on deep learning | |
| CN117973947B (en) | Standardized acceptance checking method and system for power distribution network engineering construction process | |
| CN108492013A (en) | A kind of manufacture system scheduling model validation checking method based on quality control | |
| CN107808245A (en) | Based on the network scheduler system for improving traditional decision-tree | |
| CN110956675B (en) | Method and device for automatically generating technology maturity curve | |
| CN111367255A (en) | Performance evaluation test system and method for multi-variable control system | |
| CN105740967A (en) | Manufacture cloud service execution time prediction method and manufacture cloud service execution time prediction device | |
| CN112801388B (en) | Power load prediction method and system based on nonlinear time series algorithm | |
| CN115062791A (en) | Artificial intelligence interpretation method, device, equipment and storage medium | |
| CN108615091A (en) | Electric power meteorology load data prediction technique based on cluster screening and neural network | |
| CN113962158A (en) | Road roller construction process knowledge base construction method and system based on improved decision tree | |
| CN113505818A (en) | Aluminum melting furnace energy consumption abnormity diagnosis method, system and equipment with improved decision tree algorithm |
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 |