Project management progress and quality double-control scheduling method based on big data analysis
By integrating multi-source data and using intelligent analysis, an engineering data warehouse is constructed, the intrinsic relationship between progress and quality is explored, and a dynamic scheduling model is established. This solves the problems of coordination and accuracy in progress and quality control in engineering management, and achieves efficient optimization of engineering management.
Patent Information
- Application Number
- CN202511108882.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-08-08
- Publication Date
- 2025-11-21
AI Technical Summary
Current project management suffers from limitations in progress and quality control, including single data collection dimensions, outdated analysis models, and insufficient dynamic correlation. This results in low coordination and accuracy of dual-control scheduling, making it difficult to meet the needs of multi-objective dynamic optimization in complex engineering scenarios.
By integrating multi-source data and conducting intelligent analysis, an engineering data warehouse is constructed. The analytic hierarchy process (AHP) is used to determine the weights of indicators. Machine learning algorithms are used to uncover the intrinsic relationship between progress and quality, and a progress-quality correlation model is established. A dynamic scheduling model is constructed with the goal of minimizing progress and optimizing quality. This model is then optimized in conjunction with resource and process constraints, and the scheduling scheme is monitored and adjusted in real time.
It enables dynamic and coordinated control of progress and quality in project management, improves the scientificity and accuracy of scheduling, and adapts to the multi-objective optimization needs in complex engineering scenarios.
Smart Images
Figure CN120996748A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of engineering management technology, and in particular to a dual-control scheduling method for engineering management progress and quality based on big data analysis. Background Technology
[0002] In the existing field of engineering management, schedule and quality control are usually managed by separate systems, relying on human experience for scheduling decisions. This results in problems such as limited data collection dimensions, outdated analytical models, and insufficient dynamic correlation. Traditional methods struggle to quantify the transmission effect of schedule deviations on quality risks in real time, and also cannot accurately assess the impact weight of quality control measures on schedule costs. This leads to low synergy and accuracy in dual-control scheduling, making it difficult to meet the needs of multi-objective dynamic optimization in complex engineering scenarios. Summary of the Invention
[0003] In view of this, the present invention aims to provide a project management schedule and quality dual control scheduling method based on big data analysis. Through multi-source data fusion and intelligent analysis, it realizes dynamic collaborative control of schedule and quality, thereby improving the efficiency and accuracy of project management.
[0004] The technical solution of this invention is implemented as follows:
[0005] The project management schedule and quality dual-control scheduling method based on big data analysis includes the following steps:
[0006] S1. Data Acquisition and Preprocessing Steps: Collect project progress data and quality data through IoT sensors, BIM models, and construction logs, build an engineering data warehouse, and clean, denoise, and normalize the data.
[0007] S2. Steps for constructing a dual-control scheduling indicator system: Based on the characteristics of the project, select key indicators from the dimensions of schedule and quality to construct a dual-control scheduling indicator system, and use the analytic hierarchy process (AHP) to determine the weight of each indicator;
[0008] S3. Schedule-Quality Correlation Analysis and Modeling Steps: Using big data analytics and machine learning algorithms, conduct correlation analysis on schedule and quality indicators to uncover their intrinsic connections and mutual influence mechanisms, and construct a schedule-quality correlation model and a coupling degree model.
[0009] S4. Dynamic scheduling model construction and solution steps: With the dual objectives of shortest schedule and best quality, a dynamic scheduling model is constructed considering resource constraints and process constraints. An intelligent optimization algorithm is used to solve and generate an initial scheduling scheme.
[0010] S5. Dynamic optimization steps of scheduling scheme: Feedback the initial scheduling scheme for evaluation and adjustment, monitor the project progress and quality status in real time based on big data, and dynamically optimize the scheduling scheme by adjusting resource allocation and work sequence when deviations occur;
[0011] S6. Execution Feedback and Model Iteration Steps: Issue the optimized scheduling plan for execution, collect execution data in real time for comparison and analysis with the plan, and input feedback information into the engineering data warehouse to update and improve the dual-control scheduling model.
[0012] Preferably, the data normalization process employs the min-max normalization method, with the formula being: Where X is the original data, X min X represents the maximum value of the data, and X′ represents the normalized data.
[0013] Preferably, the schedule dimension indicators include process delay rate, resource utilization rate, and critical path deviation, while the quality dimension indicators include quality defect rate, process pass rate, and quality cost ratio.
[0014] Preferably, the progress-quality correlation is calculated using the formula... Calculate, where C SQ For the correlation between schedule and quality, S k For the k-th progress indicator value, Q is the average of the schedule indicators. k For the k-th quality index value, denoted as the average value of the quality index, and l represents the sample size.
[0015] Preferably, the bi-objective optimization function of the dynamic scheduling model is: The constraints are and process constraints; where f1(T) is the schedule objective function, t i Let be the duration of the i-th process, p be the total number of processes; f2(Q) be the quality objective function, q be the number of quality indicators; r ik R represents the resource requirement of the i-th process for the k-th process. i Let r be the available quantity of the k-th resource, and r be the number of resource types.
[0016] Preferably, the machine learning algorithm includes the random forest algorithm and the support vector machine algorithm.
[0017] Preferably, the intelligent optimization algorithm includes particle swarm optimization and genetic algorithm.
[0018] Preferably, when deviations occur in the real-time monitoring of project progress and quality status, the scheduling scheme is dynamically optimized by adjusting resource allocation and process sequence.
[0019] Preferably, the process involves comparing and analyzing the project progress and quality data collected during execution with the scheduling scheme, and inputting the feedback information into the data warehouse to update and improve the dual-control scheduling model.
[0020] Preferably, the constructed engineering data warehouse is used for centralized storage and management of collected engineering progress and quality data.
[0021] The embodiments of the present invention have the following advantages due to the adoption of the above technical solutions:
[0022] Through multi-source data acquisition and preprocessing, comprehensive integration and high-quality processing of project progress and quality data were achieved. The constructed dual-control scheduling index system and correlation model clarified the mutual influence between progress and quality. The establishment of a dynamic scheduling model and optimization mechanism enables the generation of optimal scheduling schemes based on actual conditions, and allows for real-time adjustments and optimizations. This method improves the scientific rigor and accuracy of dual-control scheduling for project progress and quality, effectively solving the problem of insufficient coordination in traditional methods.
[0023] The above overview is for illustrative purposes only and is not intended to be limiting in any way. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features of the invention will become readily apparent from the accompanying drawings and the following detailed description. Attached Figure Description
[0024] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0025] Figure 1 This is a flowchart of the technical solution of the present invention.
[0026] Figure 2 This is a data flow diagram of the present invention.
[0027] Figure 3 This is the logic diagram of the dual-control scheduling model of the present invention.
[0028] Figure 4 This is a closed-loop management diagram of the present invention. Detailed Implementation
[0029] In the following description, only certain exemplary embodiments are briefly described. As those skilled in the art will recognize, the described embodiments can be modified in various ways without departing from the spirit or scope of the invention. Therefore, the drawings and description are considered to be exemplary in nature and not restrictive.
[0030] It is important to note that terms such as "first," "second," "symmetric," and "array" are used only to distinguish between descriptive and positional descriptions and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, features specified with terms such as "first" or "symmetric" may explicitly or implicitly include one or more of that feature; similarly, when the quantity of certain features is not limited by words such as "two" or "three," it should be noted that such features also explicitly or implicitly include one or more features.
[0031] In this invention, unless otherwise explicitly specified and limited, terms such as "installation," "connection," and "fixation" should be interpreted broadly; for example, they can refer to a fixed connection, a detachable connection, or an integral molding; they can refer to a mechanical connection, a direct connection, a welding connection, or an indirect connection through an intermediate medium; they can refer to the internal communication of two components or the interaction between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the accompanying drawings and specific circumstances.
[0032] The embodiments of the present invention will now be described in detail with reference to the accompanying drawings.
[0033] like Figure 1-4 The present invention provides a dual-control scheduling method for project management progress and quality based on big data analysis, comprising the following steps:
[0034] S1. Data Acquisition and Preprocessing Steps: Collect project progress data and quality data through IoT sensors, BIM models, and construction logs, build an engineering data warehouse, and clean, denoise, and normalize the data;
[0035] S2. Steps for constructing the dual-control scheduling indicator system: Based on the characteristics of the project, select key indicators from the schedule and quality dimensions to construct the dual-control scheduling indicator system, and use the analytic hierarchy process (AHP) to determine the weight of each indicator;
[0036] S3. Schedule-Quality Correlation Analysis and Modeling Steps: Using big data analytics and machine learning algorithms, conduct correlation analysis on schedule and quality indicators to uncover their intrinsic connections and mutual influence mechanisms, and construct a schedule-quality correlation model and a coupling degree model.
[0037] S4. Dynamic scheduling model construction and solution steps: With the dual objectives of shortest schedule and best quality, a dynamic scheduling model is constructed considering resource constraints and process constraints. An intelligent optimization algorithm is used to solve and generate an initial scheduling scheme.
[0038] S5. Dynamic optimization steps of scheduling scheme: Feedback the initial scheduling scheme for evaluation and adjustment, monitor the project progress and quality status in real time based on big data, and dynamically optimize the scheduling scheme by adjusting resource allocation and work sequence when deviations occur;
[0039] S6. Execution Feedback and Model Iteration Steps: The optimized scheduling scheme is executed; execution data is collected in real time and compared with the scheme for analysis; feedback information is input into the engineering data warehouse to update and improve the dual-control scheduling model; data normalization processing uses the min-max normalization method, with the following formula: Where X is the original data, X min X represents the maximum value of the data, and X′ represents the normalized data.
[0040] like Figure 1-4 As shown, the schedule dimension indicators include process delay rate, resource utilization rate, and critical path deviation, while the quality dimension indicators include quality defect rate, process pass rate, and quality cost ratio. The schedule-quality correlation is calculated using the formula... Calculate, where C SQ For the correlation between schedule and quality, S k For the k-th progress indicator value, Q is the average of the schedule indicators. k For the k-th quality index value, denoted as the average value of the quality index, and l represents the sample size.
[0041] like Figure 1-4 As shown, the bi-objective optimization function of the dynamic scheduling model is: The constraints are and process constraints; where f1(T) is the schedule objective function, t i Let be the duration of the i-th process, p be the total number of processes; f2(Q) be the quality objective function, q be the number of quality indicators; r ik R represents the resource requirement of the i-th process for the k-th process. i Let r be the available quantity of the k-th resource, and r be the number of resource types.
[0042] like Figure 1-4As shown, the machine learning algorithms include random forest algorithm and support vector machine algorithm, and the intelligent optimization algorithms include particle swarm algorithm and genetic algorithm. When deviations occur in the real-time monitoring of project progress and quality status, the scheduling scheme is dynamically optimized by adjusting resource allocation and process sequence. The project progress and quality data collected during the execution process are compared and analyzed with the scheduling scheme, and the feedback information is input into the data warehouse to update and improve the dual-control scheduling model.
[0043] like Figure 1-4 As shown, the constructed engineering data warehouse is used to centrally store and manage the collected engineering progress and quality data.
[0044] In this embodiment, the present invention operates as follows:
[0045] First, data collection and preprocessing are conducted: Extensive data on project progress (such as start and end times of each process, resource input, etc.) and quality (such as material testing data, construction process parameters, quality acceptance results, etc.) are collected from IoT sensors, BIM models, construction logs, and other channels to build an engineering data warehouse. The collected data is then cleaned to remove outliers and duplicates; noise reduction is performed to minimize interference; finally, normalization is implemented to standardize the data format and lay the foundation for subsequent analysis.
[0046] The subsequent phase involved constructing and analyzing the dual-control scheduling indicator system. Based on the project's characteristics and actual management needs, key indicators were selected from both the schedule dimension (covering process delay rate, resource utilization rate, critical path deviation, etc.) and the quality dimension (including quality defect rate, process pass rate, quality cost ratio, etc.) to build the dual-control scheduling indicator system. Using the analytic hierarchy process (AHP), professionals evaluated the importance of each indicator, determined its corresponding weight, and clarified the impact of each indicator on the dual-control scheduling.
[0047] Next, we move into the big data correlation analysis and modeling phase: using big data analytics, we conduct correlation analysis on the identified schedule and quality indicators to deeply explore their intrinsic connections and clarify how schedule changes affect quality and how quality issues are transmitted back to schedule. Using machine learning algorithms such as random forests and support vector machines, we construct a schedule-quality correlation model and a coupling degree model that quantifies the degree of synergy between the two, providing an analytical basis for subsequent scheduling.
[0048] The next stage involves constructing and solving a dynamic scheduling model. With the dual objectives of minimizing project time and optimizing quality, the model fully considers resource constraints (such as the availability of manpower, materials, and equipment) and process constraints (such as the required sequence of construction steps) to build a dynamic scheduling model. Intelligent optimization algorithms, such as particle swarm optimization and genetic algorithms, are used to solve the model, generating an initial scheduling scheme that plans the time allocation and resource distribution for each construction step.
[0049] The next stage is the optimization and adjustment of the scheduling plan: the generated initial scheduling plan is fed back to the project management personnel, who evaluate the plan based on the actual site conditions, such as construction site conditions and unforeseen circumstances, as well as their own expert experience. If any unreasonable aspects are found in the plan, such as uneven resource allocation or potential conflicts in process connections, adjustments are made promptly. Simultaneously, the actual progress and quality status of the project are monitored in real time using a big data platform. If any deviation occurs, such as a delay in a process or substandard quality inspection, the optimization mechanism is automatically triggered. This dynamically optimizes the scheduling plan by adjusting the resource allocation of subsequent processes and changing the order of process execution, ensuring the rationality of project progress.
[0050] Finally, the execution feedback and model iteration phase involves distributing the optimized scheduling plan to construction teams to guide workers in carrying out their tasks. During execution, real-time progress and quality data are collected using relevant data acquisition methods and compared with the targets set in the scheduling plan. Feedback information, including identified problems and execution results, is input into the initially constructed project data warehouse. Based on this, the parameters and algorithms in the dual-control scheduling model are continuously updated and improved, forming a closed-loop management system from plan formulation to execution feedback and model optimization. This ensures that subsequent progress and quality dual-control scheduling in project management better meets actual needs, improving management efficiency and effectiveness.
[0051] The following are several other specific embodiments of the application of this invention:
[0052] Example 1: High-rise building construction scenario
[0053] Data Acquisition and Preprocessing
[0054] Deploy smart safety helmets and construction elevator sensors to collect progress data such as personnel attendance and material transportation (e.g., construction cycle of each floor of the main structure and completion rate of rebar binding), and combine this with concrete curing sensors and rebound hammer test data to obtain quality information (e.g., concrete strength growth curve and floor slab flatness).
[0055] Build a data warehouse for high-rise buildings, clean up false transportation records caused by signal interference from elevator sensors, denoise concrete strength data (remove the influence of curing environment fluctuations), and normalize personnel attendance data (0-100%).
[0056] Indicator System and Correlation Analysis
[0057] Progress indicators: construction floor difference of main structure (deviation between actual and planned number of floors), utilization rate of vertical transportation equipment (tower crane, construction elevator), and proportion of night construction (overtime intensity affecting progress).
[0058] Quality indicators: Concrete strength qualification rate (≥90% of design value), formwork joint leakage defect rate, and hollow area rate during the decoration stage.
[0059] Correlation analysis revealed that when nighttime construction accounted for more than 40% of the total construction work, the pass rate of concrete curing quality decreased by 12% (correlation degree 0.78), due to the slow strength growth caused by the low nighttime temperature.
[0060] Dynamic scheduling and optimization
[0061] The dual-objective model aims to minimize the total construction period of the main structure, maximize the concrete strength qualification rate, and constrain the number of daily tower crane hoisting operations (≤80 times) and the number of workers at night (≤60% of the total number of workers).
[0062] Genetic algorithm solution: Generate scheduling scheme. During winter construction, prioritize daytime concrete pouring (to improve curing quality) and simultaneously increase the daytime lifting frequency of tower cranes (progress loss ≤5%, quality pass rate increased to 95%). In summer, utilize the cool nighttime hours for construction to reduce the risk of concrete hydration heat.
[0063] Real-time optimization: When the system detects that the concrete strength growth of a certain floor is lagging behind (not reaching 80% of the design value in 3 days), it automatically adjusts the pouring time of subsequent floors (delaying by 2 days to avoid insufficient curing due to continuous construction) and adds curing spray equipment (quality cost +2%, to ensure that the strength meets the standard).
[0064] Execution feedback and model iteration
[0065] By inputting the "season-construction period-quality association rules" (such as prioritizing daytime pouring in winter and nighttime pouring in summer) into the data warehouse, the updated model can automatically recommend the optimal construction period based on real-time weather data, reducing the quality rework rate by more than 20%.
[0066] Example 2: Municipal Road Engineering Scenario
[0067] Data acquisition and end-to-end monitoring
[0068] Collect roadbed construction progress (such as earthwork backfill compaction degree and base course paving area) and pavement construction quality data (asphalt mixture temperature and pavement smoothness standard deviation), and combine them with traffic flow simulation data (the impact of detours on the progress during construction) to build a road engineering data warehouse.
[0069] Preprocessing: Time series normalization was performed on the asphalt temperature data (converted to [0,1] according to the paving period 0-140℃) to remove invalid detour schemes in the traffic flow simulation.
[0070] Indicators and Correlation Modeling
[0071] Progress indicators: roadbed construction section difference (deviation between actual and planned mileage), utilization rate of key equipment (pavers, rollers), and traffic diversion delay rate (delay in material transportation due to detours).
[0072] Quality indicators: road surface smoothness (≤3mm / 3m), asphalt mixture gradation pass rate, and subgrade settlement exceeding standard rate (≤1%).
[0073] Correlation analysis revealed that when the paver's travel speed exceeded the planned speed by 15%, the road surface smoothness pass rate decreased by 10% (correlation degree 0.85), due to uneven paving caused by excessive speed.
[0074] Dynamic scheduling and collaborative management
[0075] Dual-objective optimization: minimize road opening time, maximize road surface smoothness pass rate, and constrain the daily working time of pavers (≤10 hours) and traffic diversion plan (detour distance ≤2km).
[0076] Particle swarm optimization algorithm solution: Generate scheduling scheme, increase paver speed (≤110% of plan) during low traffic hours (such as at night), and simultaneously increase the number of compaction cycles of the roller (quality cost +3%, smoothness pass rate increased to 98%); during peak traffic hours, reduce paving speed (ensure smoothness, progress loss ≤3%).
[0077] Real-time optimization: When a sudden traffic accident causes a 2-hour delay in material transportation, the system automatically adjusts the subsequent paving process (prioritizing the use of stock mixed materials, and simultaneously notifying the supplier to expedite transportation to avoid equipment being idle for more than 30 minutes).
[0078] Model iteration and scene adaptation
[0079] The model is updated with parameters related to "traffic conditions-construction speed-quality" (such as the paving speed threshold during peak hours). This allows the model to automatically adapt to traffic flow and dynamically adjust the construction pace when constructing on main urban roads, thereby reducing potential quality issues caused by rushing the schedule.
[0080] Example 3: Steel Structure Engineering Scenario for Industrial Plants
[0081] Data Acquisition and Component Management
[0082] Collect data on the processing progress of steel components (such as the completion time of steel beam welding and the accuracy of bolt holes) and the on-site hoisting progress (daily hoisting tonnage and component installation verticality), and combine this data with the node connection parameters of the steel structure BIM model to build a data warehouse for the factory project.
[0083] Preprocessing: Standardize the bolt hole accuracy data (±0.5mm is converted to [-1,1]) and clean up false verticality data caused by wind interference from the hoisting sensors.
[0084] Indicators and Correlation Analysis
[0085] Progress indicators: steel component processing-hoisting cycle (≤10 days / span), utilization rate of welding equipment (robot welding machine), and idle rate of hoisting machinery (crawler crane).
[0086] Quality indicators: Node connection strength qualification rate (≥95% of design value), component installation verticality deviation (≤5mm), welding defect rework rate (≤2%).
[0087] Correlation analysis revealed that when the utilization rate of welding equipment was below 70%, the pass rate of node connection strength decreased by 8% (correlation degree 0.79), which was due to parameter drift caused by the long-term idleness of the welding machine.
[0088] Dynamic scheduling and quality pre-control
[0089] The dual-objective model aims to minimize the total construction period of the steel structure of the factory building, maximize the pass rate of node connection strength, and constrain the number of daily calibrations of the welding machine (≥1 time) and the lifting radius of the crawler crane (≤30m).
[0090] Ant colony algorithm solution: Generate scheduling scheme, prioritize welding tasks of high difficulty nodes (improve welding machine utilization to ≥85%), and simultaneously optimize hoisting sequence (install high precision columns first, then hoist crossbeams to reduce the number of verticality adjustments).
[0091] Real-time optimization: When the welding machine calibration data is abnormal (deviation ±0.3mm), the system automatically triggers the welding parameter reset (completed within 1 hour) and adjusts the order of subsequent welding tasks (welding components with low precision requirements first, and processing high precision nodes after calibration is completed).
[0092] Closed-loop management and process optimization
[0093] The "welding equipment status-quality" association rules (such as calibration strategies when utilization is below a threshold) are fed back to the model. After the update, the welding machine status is automatically monitored and early warnings are issued in similar projects, reducing quality rework caused by equipment problems and improving the accuracy of progress-quality coordination in steel structure engineering.
[0094] The above description is merely a specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any person skilled in the art can easily conceive of various variations or substitutions within the technical scope disclosed in the present invention, and these should all be included within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.
Claims
1. A project management scheduling method based on big data analysis with dual control over schedule and quality, characterized in that, Includes the following steps: S1. Data Acquisition and Preprocessing Steps: Collect project progress data and quality data through IoT sensors, BIM models, and construction logs, build an engineering data warehouse, and clean, denoise, and normalize the data. S2. Steps for constructing a dual-control scheduling indicator system: Based on the characteristics of the project, select key indicators from the dimensions of schedule and quality to construct a dual-control scheduling indicator system, and use the analytic hierarchy process (AHP) to determine the weight of each indicator; S3. Schedule-Quality Correlation Analysis and Modeling Steps: Using big data analytics and machine learning algorithms, conduct correlation analysis on schedule and quality indicators to uncover their intrinsic connections and mutual influence mechanisms, and construct a schedule-quality correlation model and a coupling degree model. S4. Dynamic scheduling model construction and solution steps: With the dual objectives of shortest schedule and best quality, a dynamic scheduling model is constructed considering resource constraints and process constraints. An intelligent optimization algorithm is used to solve and generate an initial scheduling scheme. S5. Dynamic optimization steps of scheduling scheme: Feedback the initial scheduling scheme for evaluation and adjustment, monitor the project progress and quality status in real time based on big data, and dynamically optimize the scheduling scheme by adjusting resource allocation and work sequence when deviations occur; S6. Execution Feedback and Model Iteration Steps: Issue the optimized scheduling plan for execution, collect execution data in real time for comparison and analysis with the plan, and input feedback information into the engineering data warehouse to update and improve the dual-control scheduling model.
2. The project management schedule and quality dual-control scheduling method based on big data analysis according to claim 1, characterized in that: The data normalization process employs the min-max normalization method, as shown in the formula: Where X is the original data, X min X represents the maximum value of the data, and X′ represents the normalized data.
3. The engineering management schedule and quality dual control scheduling method based on big data analysis according to claim 1, characterized in that: The schedule dimension indicators include process delay rate, resource utilization rate, and critical path deviation, while the quality dimension indicators include quality defect rate, process pass rate, and quality cost ratio.
4. The project management schedule and quality dual-control scheduling method based on big data analysis according to claim 1, characterized in that: The progress-quality correlation is calculated using the formula. Calculate, where C SQ For the correlation between schedule and quality, S k For the k-th progress indicator value, Q is the average of the schedule indicators. k For the k-th quality index value, denoted as the average value of the quality index, and l represents the sample size.
5. The project management schedule and quality dual control scheduling method based on big data analysis according to claim 1, characterized in that: The bi-objective optimization function of the dynamic scheduling model is: The constraints are and process constraints; where f1(T) is the schedule objective function, t i Let be the duration of the i-th process, p be the total number of processes; f2(Q) be the quality objective function, q be the number of quality indicators; r ik R represents the resource requirement of the i-th process for the k-th process. i Let r be the available quantity of the k-th resource, and r be the number of resource types.
6. The engineering management schedule and quality dual-control scheduling method based on big data analysis according to claim 1, characterized in that: The machine learning algorithms include the random forest algorithm and the support vector machine algorithm.
7. The project management schedule and quality dual control scheduling method based on big data analysis according to claim 1, characterized in that: The intelligent optimization algorithms include particle swarm optimization and genetic algorithms.
8. The project management schedule and quality dual control scheduling method based on big data analysis according to claim 1, characterized in that: When deviations occur in the real-time monitoring of project progress and quality status, the scheduling scheme is dynamically optimized by adjusting resource allocation and process sequence.
9. The engineering management schedule and quality dual-control scheduling method based on big data analysis according to claim 1, characterized in that: The process involves comparing and analyzing the project progress and quality data collected during execution with the scheduling scheme, and inputting the feedback information into the data warehouse to update and improve the dual-control scheduling model.
10. The engineering management schedule and quality dual-control scheduling method based on big data analysis according to any one of claims 1-9, characterized in that: The constructed engineering data warehouse is used for centralized storage and management of collected engineering progress and quality data.