CN113627735A - Early warning method and system for safety risk of engineering construction project - Google Patents
Early warning method and system for safety risk of engineering construction project Download PDFInfo
- Publication number
- CN113627735A CN113627735A CN202110810537.4A CN202110810537A CN113627735A CN 113627735 A CN113627735 A CN 113627735A CN 202110810537 A CN202110810537 A CN 202110810537A CN 113627735 A CN113627735 A CN 113627735A
- Authority
- CN
- China
- Prior art keywords
- data
- early warning
- engineering construction
- construction project
- emergency plan
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 85
- 238000010276 construction Methods 0.000 title claims abstract description 76
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 26
- 238000005457 optimization Methods 0.000 claims abstract description 24
- 238000012706 support-vector machine Methods 0.000 claims abstract description 21
- 239000002245 particle Substances 0.000 claims abstract description 20
- 230000008569 process Effects 0.000 claims abstract description 18
- 230000010485 coping Effects 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims description 70
- 238000012544 monitoring process Methods 0.000 claims description 66
- 239000011159 matrix material Substances 0.000 claims description 18
- 238000004458 analytical method Methods 0.000 claims description 11
- 230000002159 abnormal effect Effects 0.000 claims description 9
- 238000012502 risk assessment Methods 0.000 claims description 7
- 238000012854 evaluation process Methods 0.000 claims description 5
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000013058 risk prediction model Methods 0.000 claims description 4
- 238000012163 sequencing technique Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 claims description 3
- QVFWZNCVPCJQOP-UHFFFAOYSA-N chloralodol Chemical compound CC(O)(C)CC(C)OC(O)C(Cl)(Cl)Cl QVFWZNCVPCJQOP-UHFFFAOYSA-N 0.000 claims description 3
- 238000007405 data analysis Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 description 21
- 230000006870 function Effects 0.000 description 9
- 230000006872 improvement Effects 0.000 description 8
- 238000012360 testing method Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 239000000126 substance Substances 0.000 description 4
- 238000010219 correlation analysis Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000013077 scoring method Methods 0.000 description 3
- 238000012216 screening Methods 0.000 description 3
- 238000004062 sedimentation Methods 0.000 description 3
- 230000001186 cumulative effect Effects 0.000 description 2
- 230000007613 environmental effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000005452 bending Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 230000009469 supplementation Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0635—Risk analysis of enterprise or organisation activities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/10—Office automation; Time management
- G06Q10/103—Workflow collaboration or project management
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Data Mining & Analysis (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention provides an early warning method and system for safety risks of engineering construction projects. According to the early warning method, the interference of data with errors on a risk prediction process is avoided by acquiring and processing sample data of an engineering construction project, so that the sample data is accurate and reliable; on the basis, the single-factor short-term prediction is carried out by constructing a time sequence model, and the support vector machine model optimized by the particle swarm optimization algorithm is constructed to carry out multi-factor system prediction, so that a layered engineering construction project safety risk early warning model is formed, and the engineering construction project safety risk is comprehensively and effectively predicted and early warned; then, the corresponding alternative emergency plans are further extracted according to the obtained early warning condition, and the alternative emergency plans are evaluated in a mode of fusing a cloud model and an ideal point method to obtain an optimal emergency scheme, so that the risk is effectively early warned, and an effective coping scheme is provided to meet the requirements of practical application.
Description
Technical Field
The invention relates to the technical field of construction project safety risk early warning, in particular to an early warning method and system for safety risks of engineering construction projects.
Background
Along with the progress of society, the scale of engineering construction projects is gradually enlarged, the development is continuously accelerated, the standards and requirements for construction technology and safety management are gradually improved, the function of safety risk early warning in the safety of the engineering construction projects is widely recognized, and safety early warning systems are adopted to carry out cooperative management in the construction of the engineering construction projects in various places. At present, many safety early warning systems related to engineering construction projects exist, the degree and the content of each system have certain differences, but most of the safety early warning systems which are put into use at present are relatively simple, and have great limitations in practical application.
For example, patent publication No. CN112863119A provides an engineering construction safety risk early warning system and method, in which a strain gauge is arranged to collect structural risk data such as deformation and displacement of a monitoring point, an environment collection module is arranged to collect environmental factor data such as temperature, humidity, air volume, and harmful gas concentration in a construction environment, the structural risk data and the environmental factor data are respectively input into corresponding risk judgment functions, and corresponding risk early warning signals are sent according to output results, so as to achieve real-time, wireless, and efficient construction safety early warning effects. However, the method judges the risk data only through the risk judgment function, the judgment mode is too single, actually, the accident causes are usually complicated, and the method provided by the patent is difficult to give a comprehensive early warning to various risks.
The patent with publication number CN111508216A provides an intelligent early warning method for dam safety monitoring data, which has a wide application range, although different models and indexes such as a stepwise regression model, a correlation vector machine model, a gray system model are established according to monitoring items, independent variable correlation, the quantity of historical monitoring data and the distribution of historical monitoring data. However, because of lack of hierarchy among various analysis models, more models need to be set for analysis, the overall computation is large, and the actual efficiency is not high; meanwhile, the patent cannot further provide a corresponding emergency plan after the early warning is sent out, the early warning information still needs to be analyzed manually, risk reasons are confirmed, the corresponding emergency plan is formulated, and the overall intelligence is low.
In view of the above, there is a need for an improved method and system for early warning of safety risk of engineering construction project to solve the above problems.
Disclosure of Invention
In view of the above-mentioned defects of the prior art, the present invention aims to provide a method and a system for early warning of safety risks of engineering construction projects. Single-factor short-term prediction is carried out by constructing a time sequence model, and meanwhile, a support vector machine model optimized by a particle swarm optimization algorithm is constructed to carry out multi-factor system prediction, so that a layered engineering construction project safety risk early warning model is formed, and the engineering construction project safety risk is comprehensively and effectively predicted and early warned; and extracting a corresponding alternative emergency plan according to the obtained early warning condition, and evaluating the alternative emergency plan by adopting a mode of fusing a cloud model and an ideal point method to obtain an optimal emergency scheme, so that an effective coping scheme is provided while efficient early warning is carried out on risks, and the requirement of practical application is met.
In order to achieve the purpose, the invention provides an early warning method for the safety risk of an engineering construction project, which comprises the following steps:
s1, collecting sample data of the engineering construction project and processing the sample data;
s2, establishing a hierarchical engineering construction project safety risk early warning model, and performing risk prediction on the processed sample data obtained in the step S1; the risk prediction model comprises a time series model for single-factor short-term prediction and a support vector machine model which is used for multi-factor system prediction and optimized by a particle swarm optimization algorithm;
and S3, extracting an alternative emergency plan according to the conclusion obtained by the risk prediction in the step S2, and evaluating the alternative emergency plan to generate an optimal emergency plan.
As a further improvement of the present invention, in step S3, the candidate emergency plan is evaluated in a manner of fusing a cloud model and an ideal point method, and the evaluation process includes the following steps:
s31, constructing an evaluation index system of the emergency plan, and establishing an evaluation scheme decision matrix of the emergency plan;
s32, determining a decision attribute cloud parameter matrix of the emergency plan;
s33, determining the attribute weight of the emergency plan;
s34, determining a positive ideal value and a negative ideal value of the emergency plan;
s35, calculating the weighted distance between each alternative emergency plan and the positive ideal value and the negative ideal value;
and S36, calculating the closeness of each alternative coping plan, sequencing the alternative coping plans according to the closeness, and taking the alternative coping plan with the maximum closeness as an optimal emergency scheme.
As a further improvement of the present invention, in step S33, the attribute weight of the emergency plan is obtained by combined weighting using a network hierarchy analysis method and a gray correlation method based on the principle of minimum deviation.
As a further improvement of the present invention, in step S3, the candidate emergency plan is extracted based on a two-stage similarity algorithm, which includes firstly calculating a feature attribute by using a local similarity algorithm, then respectively accumulating the feature attribute value of the current case and each historical case in the emergency plan library by using an overall similarity algorithm to obtain an overall similarity corresponding to each historical case, and using the historical case corresponding to the case when the overall similarity is greater than a preset threshold as the candidate emergency plan.
As a further improvement of the present invention, in step S1, the sample data includes monitoring data and safety risk assessment data for the engineering construction project.
As a further improvement of the present invention, in step S1, the processing of the monitoring data includes coarse error analysis of the monitoring data based on a modified grubbs criterion and interpolation processing of missing data in the monitoring data based on a cubic spline interpolation method; the processing of the security risk assessment data includes obtaining an expected value of the security risk assessment data.
As a further improvement of the present invention, in step S1, the gross error analysis includes the following steps:
s11, calculating the suspected maximum value and the suspected minimum value of the monitoring data, and acquiring a Grabbs criterion critical value;
s12, comparing the suspected maximum value, the suspected minimum value and the critical value, and identifying and eliminating abnormal data in the monitoring data;
and S13, repeating the steps S11-S12, and repeatedly identifying and eliminating the monitoring data until the monitoring data has no abnormal value.
As a further improvement of the present invention, in step S2, the time series model is an autoregressive moving average model for performing single-factor short-term prediction on the monitoring data processed in step S1; and the support vector machine model optimized by the particle swarm optimization algorithm is used for carrying out multi-factor system prediction on the safety risk evaluation data processed in the step S1.
In order to achieve the above object, the present invention further provides an early warning system for engineering construction project safety risk, which is used for executing the early warning method according to the above technical solution, and the early warning system comprises:
the data acquisition module is used for acquiring and transmitting monitoring data in real time;
the data processing module is used for processing abnormal data in the monitoring data acquired by the data acquisition module;
the data analysis module is used for establishing a safety risk early warning model of the engineering construction project and carrying out risk early warning on the data processed by the data processing module;
the plan generating module is used for extracting an alternative emergency plan according to the risk early warning result output by the data analyzing module and generating an optimal emergency plan by evaluating the alternative emergency plan;
the storage module is used for storing basic data of the engineering construction project and monitoring data acquired by the data acquisition module;
and the control module is used for controlling the operation of the system and managing the user information.
As a further improvement of the invention, the data acquisition module comprises a wireless sensor network for acquiring monitoring data in real time and a data transmission unit based on the LoRa technology.
The invention has the beneficial effects that:
(1) according to the invention, single-factor short-term prediction is carried out by constructing the time sequence model, and the support vector machine model optimized by the particle swarm optimization algorithm is constructed for multi-factor system prediction, so that a hierarchical engineering construction project safety risk early warning model can be formed, and the engineering construction project safety risk can be comprehensively and effectively predicted and early warned. On the basis, the method and the system can also extract the corresponding alternative emergency plan according to the prediction result obtained by the risk early warning model, evaluate the alternative emergency plan by adopting a mode of fusing a cloud model and an ideal point method, and generate an optimal emergency plan, so that the risk is effectively early warned, an effective coping scheme is provided, and the method and the system have high practical application value.
(2) The hierarchical engineering construction project safety risk early warning model constructed by the method can predict the single-factor short-term risk condition under the condition of only considering timeliness, and can predict the multi-factor system level by considering the relevance characteristics among multiple factors. Before prediction is carried out by using the autoregressive moving average model, coarse error analysis is carried out on monitoring data by using an improved Grubbs criterion, and then interpolation processing is carried out on missing data in the monitoring data by using a cubic spline interpolation method, so that interference of data with errors on a risk prediction process is effectively avoided, and the reliability and the accuracy of the monitoring data are ensured. Meanwhile, the support vector machine model is optimized by utilizing a particle swarm optimization algorithm so as to obtain the parameter combination with the minimum root mean square error and the highest classification accuracy of the decision function, thereby effectively reducing the error and improving the stability of the prediction result.
(3) On the basis of accurately predicting and early warning the safety risk of the engineering construction project, the invention adopts a two-stage similarity algorithm to efficiently extract the case situation similar to the current case from the engineering construction project safety accident case library to be used as a standby emergency plan. In addition, in order to ensure that the most suitable emergency plans are obtained, the alternative emergency plans are evaluated in a mode of fusing a cloud model and an ideal point method, the optimal emergency plan is determined by sequencing the closeness of the alternative emergency plans, and related workers are assisted to make decisions in time according to the early warning condition so as to meet the requirements of practical application.
(4) When the method adopts a mode of fusing the cloud model and the ideal point method to evaluate the alternative emergency plan, the statistical method is used for counting and calculating the opinion concentration degree and the opinion coordination degree of each expert on the basis of the scoring of the experts, the objectivity and the reliability of the screening process are effectively improved, a representative emergency plan evaluation index system is established, and a network analytic hierarchy process and a gray correlation method based on the minimum deviation principle are further adopted to carry out combined weighting on the emergency plan evaluation indexes. In the process of combined weighting, the network analytic hierarchy process adopted by the invention can fully consider the relevance among all indexes compared with the conventional analytic hierarchy process, and is more in line with the characteristic that the indexes in an emergency plan have mutual influence; on the basis, the method determines the parent index of the grey correlation analysis process according to the subjective weight obtained by the network analytic hierarchy process, and performs grey correlation analysis according to the parent index to improve the accuracy of the objective weight, so that the subjective weight and the objective weight are effectively combined, more accurate and objective index weight is obtained, and a representative and scientific emergency plan evaluation index system is constructed to improve the scientificity and accuracy of the evaluation process.
Drawings
Fig. 1 is a schematic flow diagram of an early warning method for safety risks of an engineering construction project according to the present invention.
Fig. 2 is a schematic diagram of an early warning flow of a support vector machine model optimized by a particle swarm optimization algorithm in the early warning method provided by the invention.
Fig. 3 is an emergency plan evaluation index system established when an alternative emergency plan is evaluated in the early warning method provided by the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in detail with reference to the accompanying drawings and specific embodiments.
It should be noted that, in order to avoid obscuring the present invention with unnecessary details, only the structures and/or processing steps closely related to the aspects of the present invention are shown in the drawings, and other details not closely related to the present invention are omitted.
In addition, it is also to be noted that the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus.
The invention provides an early warning method for safety risks of engineering construction projects, which is shown in a flow diagram in figure 1 and comprises the following steps:
s1, collecting sample data of the engineering construction project and processing the sample data;
s2, establishing a hierarchical engineering construction project safety risk early warning model, and performing risk prediction on the processed sample data obtained in the step S1; the risk prediction model comprises a time series model for single-factor short-term prediction and a support vector machine model which is used for multi-factor system prediction and optimized by a particle swarm optimization algorithm;
and S3, extracting an alternative emergency plan according to the conclusion obtained by the risk prediction in the step S2, and evaluating the alternative emergency plan to generate an optimal emergency plan.
In one embodiment of the invention, the safety risk of the subway construction project is pre-warned by taking the subway construction project as an example. It should be noted that, in other embodiments of the present invention, the safety risk of other various engineering construction projects can be pre-warned in the same manner, and all of them belong to the protection scope of the present invention.
Specifically, when the embodiment takes a subway construction project as an example to perform safety risk early warning, the method includes the following steps:
and S1, collecting monitoring data and safety risk evaluation data of the engineering construction project, and preprocessing various data.
The safety risk evaluation data are collected in a mode of issuing questionnaires to obtain expected values of the safety risk evaluation data; the monitoring data is derived from the accumulated settlement original data of the actual foundation pit monitoring points in a certain subway construction project, and comprises monitoring data of five monitoring points XF1-1, XF1-2, XF1-3, XF1-4, XF1-5 in XF1 and five monitoring points XF2-1, XF2-2, XF2-3, XF2-4 and XF2-5 in XF 2. The accumulated settling volume raw data for each monitoring point in XF1 and XF2 are shown in table 1.
Table 1 XF1 and XF2 shows the cumulative settling volume raw data for each monitoring point
In Table 1, "-" represents the raw data missing from the monitoring point.
Due to the influence of external factors in the data monitoring process, errors may exist, and the data with the errors interfere with prediction of risks and need to be removed. In this embodiment, an improved grassbloss criterion is adopted to perform gross error analysis on the monitoring data, and a median is introduced to replace an average number, so as to meet research requirements when a plurality of abnormal values are detected, thereby ensuring reliability and accuracy of the monitoring data, and the specific analysis steps are as follows:
s11, calculating the suspected maximum value and the suspected minimum value of the monitoring data according to the following formula, and obtaining the Grabbs criterion critical value G by looking up the table(a,n):
Wherein G ismaxA pseudo-maximum value representing the sequence { X }; gminA pseudo-minimum value representing the sequence { X }; xmaxRepresents the maximum value of the array { X }; xminRepresents the minimum value of the array { X }; mcRepresents a median; s represents a standard deviation.
S12, comparing the suspected maximum value GmaxThe suspected minimum value GminAnd a critical value G(a,n)If G ismax>G(a,n)Or Gmin>G(a,n)Then the corresponding culling Xmax、Xmin。
And S13, repeating the steps S11-S12, and repeatedly identifying and eliminating the monitoring data until the monitoring data has no abnormal value.
In this embodiment, the threshold value G of the grassbs criterion is obtained by referring to the table of the grassbs threshold value according to the monitoring data(30,0.05)2.745, the 2.3mm in monitor point XF1-5 is the maximum of all data, corresponding to the suspected maximum Gmax4.413 due to Gmax>G(30,0.05)Therefore, 2.3mm needs to be rejected. For this reason, the present embodiment analyzes only data of the first 25 th period of the monitoring period.
Meanwhile, as the original data of the monitoring points still have deficiency, the missing data also needs to be interpolated. In this embodiment, a cubic spline interpolation method is used to interpolate missing data in monitoring data, and a triple bending moment method is specifically used to perform calculation, and the following steps are performed:
(1) selecting the second derivative as the undetermined parameter, mk=S″(xk),k=0,1,…,n。
(2) Deriving cubic spline interpolation S (x) from the conditionsi) In the k-th interval [ x ]k,xk+1]And (b) as shown in the following formula:
S(x)=Sk1(x-xk)3+Sk2(x-xk)2+Sk3(x-xk)1+Sk4
(3) since the first derivatives are equal, the basic equation of the triple moment method can be derived as follows:
wherein the content of the first and second substances,dk=f[xk-1,xk,xk+1];d0=f[x0,x1];dn=f[xn-1,xn]。
(4) natural conditions are selected as boundary conditions, namely: m is0=mnThe above formula is substituted for 0.
According to the method, MATLABR2010b is adopted for calculation, and the accumulated sedimentation amount data of monitoring points XF1 and XF2 after the supplementation is lost are finally obtained, as shown in Table 2.
Table 2 XF1 and XF2 raw data for cumulative settling volume for each monitoring point
And forming a complete time series data chain based on the coarse error analysis of the monitoring data by the improved Grubbs criterion and the interpolation processing of missing data in the monitoring data by a cubic spline interpolation method.
And S2, establishing a hierarchical engineering construction project safety risk early warning model, and performing risk prediction on the processed sample data obtained in the step S1.
The risk prediction model comprises a time series model for single-factor short-term prediction and a support vector machine model which is used for multi-factor system prediction and optimized by a particle swarm optimization algorithm.
Specifically, according to the complete time series data chain obtained in step S1, in this embodiment, taking the data of the monitoring point XF1-4 as an example, an autoregressive moving average (ARMA) model in the time series is used to perform single-factor short-term prediction on the monitoring data, and the specific method is as follows:
the stability test statistic of the accumulated sedimentation amount original data of the monitoring point is-3.602117 and is obviously larger than the critical values of 1% and 5% by using Eviews software through ADF test, and the original hypothesis that a unit root exists is received, wherein P is 0.0510 to 0.05. Because the accumulated sedimentation amount of the monitoring point is non-stationary data, the data sequence needs to be subjected to first-order difference processing, namely d is 1, the statistical quantity obtained by ADF test is-6.467746, the critical value is obviously less than 1%, 5% and 10%, and P is less than 0.0001, so that the original hypothesis is rejected. And after differential processing, a stationarity time sequence is obtained, and modeling can be carried out on the stationarity time sequence.
The least square estimation method is adopted to minimize the sum of squared residuals, and the result is that when the order n is l and m is 1, the value of AIC 3.318256 reaches the minimum value, and the model is determined to be ARMA (1, 1). And testing model residuals, wherein the values of the statistics are all larger than 0.05, and the statistics pass the significance test.
Then, according to the predicted data of the accumulated settlement amounts of 20 th, 21 th, 22 th, 23 th, 24 th and 25 th at the monitoring point XF1-4, the actual data and the predicted data are compared, and the result is shown in Table 3.
TABLE 3 comparison of actual and predicted data
As can be seen from Table 3, the prediction precision is good, the fitting result is good, the comparison between the actual data and the predicted data is basically consistent, and the ARMA (1, 1) can be effectively used for predicting the single-factor short-term risk condition of the safety risk of the engineering construction project.
On the basis, a support vector machine model optimized by a particle swarm optimization algorithm is further adopted to carry out multi-factor system prediction on safety risk evaluation data, a flow diagram of the method is shown in FIG. 2, and the method specifically comprises the following steps:
(1) and constructing a safety risk evaluation index system of the engineering construction project, and acquiring expected values E of safety risk evaluation data corresponding to each evaluation index in a mode of issuing questionnaires. Here, the expectation value E ═ Σ index score × comprehensive weight ω.
In this embodiment, 18 groups of safety risk evaluation data are collectively collected, and the expected values of the safety risk evaluation data of each group are shown in table 4, wherein 1 to 12 groups are used as training samples of the safety risk early warning model, and 13 to 18 groups are used as inspection samples of the safety risk early warning model.
TABLE 4 expected values of safety Risk assessment data
Sample data | E | Sample data | E | Sample data | E |
1 | 0.7187 | 7 | 0.7194 | 13 | 0.8400 |
2 | 0.7706 | 8 | 0.7338 | 14 | 0.7726 |
3 | 0.7267 | 9 | 0.8399 | 15 | 0.8321 |
4 | 0.7228 | 10 | 0.7770 | 16 | 0.7689 |
5 | 0.8219 | 11 | 0.8283 | 17 | 0.8041 |
6 | 0.7728 | 12 | 0.7781 | 18 | 0.8247 |
(2) Setting search parameter C1=1.5,C2=1.5;g∈[2-10,210](ii) a The number of iterations is Max 200; the population number N is 20; the inertial weight ω is 1.
(3) Optimizing by adopting a 2-CV mode, obtaining a parameter C which is 2.0985 and g which is 0.01 after the particle swarm optimization algorithm is optimized through calculation, obtaining a mean square error MSE which is 0.010631 and obtaining a variance R2=0.97964。
In order to test the optimization effect of the particle swarm optimization algorithm, a support vector machine model which is not optimized by parameters is established, the mean square error MSE of the support vector machine model is 0.025458, and the variance R is obtained2=0.96952。
The prediction of 13-18 groups of safety risk evaluation data as test samples is carried out according to the two modes, and the comparison of the predicted value and the real expected value E (x) and the relative error and variance are shown in Table 5.
TABLE 5 comparison of the error of the prediction results of the unoptimized support vector machine model (SVM) and the optimized support vector machine model (PSO-SVM) by the particle swarm optimization algorithm
As can be seen from Table 5, the error fluctuation stability of the support vector machine model optimized by the particle swarm optimization algorithm provided by the invention is obviously superior to that of the model which is not optimized, the prediction result is relatively stable, and the application value is higher. The main reasons for this are: the punishment parameters and the parameters of the kernel function can be searched together through particle swarm optimization algorithm optimization, the optimal combination of the punishment parameters and the parameters of the kernel function is realized, and a better prediction effect is achieved.
According to the prediction result of the support vector machine model optimized by the particle swarm optimization algorithm, the support vector machine model is divided into corresponding risk levels and alarm situations according to the mode shown in the table 6, and corresponding early warning is sent out.
TABLE 6 engineering construction project safety risk level and Warning situation
Scoring | Risk rating | Whether there is an alert |
[0,0.3] | Big (a) | Severe degree |
[0.3,0.5] | In | Of moderate degree |
[0.5,0.7] | Small | In general |
[0.7,1.0] | Is smaller | Small |
And S3, extracting an alternative emergency plan according to the risk grade of the evaluation index obtained by the risk prediction in the step S2, and evaluating the alternative emergency plan to generate an optimal emergency plan.
As the safety accidents of the engineering project comprise different types of accidents, the characteristic attributes of the accidents also have diversity, including numerical type, symbolic type and fuzziness. Based on this, the embodiment extracts the alternative emergency plans based on the two-stage similarity algorithm, and includes the following steps:
(1) the local similarity algorithm is adopted to calculate three characteristic attributes of the font attribute, the symbolic attribute and the fuzziness attribute, and the calculation formula is as follows:
digital attribute similarity Sim (X)i,Yi)=1-(Xi-Yi)/|maxi-mini|
Wherein, Sim (X)i,Yi) Representing the similarity of the ith determinant attributes of cases X and Y; xi,YiValues representing i attributes for cases X and Y; maxiAnd miniThe maximum and minimum values of the ith attribute are indicated. The similarity between the digital attribute and the symbolic attribute is generally between 0 and 1, and the closer to 1 indicates that the i attributes of X and Y have high similarity, and the lower the similarity is otherwise.
Wherein the content of the first and second substances,the Wasserstein distance representing the ith determinant attribute of X and Y.
(2) And respectively accumulating the characteristic attribute values of the current case and the historical cases in the emergency plan library by adopting an overall similarity calculation method to obtain overall similarities respectively corresponding to the historical cases, wherein the calculation formula is as follows:
wherein Sim (T, C) represents the overall similarity value of the historical case T and the current case C; omegai、ωijRepresenting the ith primary and secondary feature attribute weight values; sim (T)ij,Cij) Local similarity values representing the T and C secondary characteristic attributes; n, miAnd the number of the first-level and second-level characteristic attributes is represented.
In this embodiment, the threshold δ is set in advance to be 80%, and when the overall similarity value calculated in the above manner is greater than 80%, the corresponding history case is extracted as the candidate emergency plan.
After the candidate emergency plan is obtained, in order to select an optimal emergency plan from the candidate emergency plan, the embodiment evaluates the candidate emergency plan by using a mode of fusing a cloud model and an ideal point method, and the evaluation process specifically includes the following steps:
s31, constructing an evaluation index system of the emergency plan, and establishing a decision matrix of the emergency plan evaluation scheme.
In the embodiment, a preliminary emergency plan evaluation index is obtained based on a rooting theory, each index is quantized by adopting an expert scoring method, and the concentration degree and coordination degree of opinions of each expert are counted and calculated by utilizing a statistical method, so that the objectivity and reliability of the index screening process are improved, and a representative emergency plan evaluation index system is established.
Wherein the concentration degree of the opinions is determined by the average number (M)j) And full frequency (K)j) The measure is carried out, and the degree of coordination of the opinions is determined by the coefficient of variation (V)j) And a coordination coefficient (ω).
The coordination coefficient (omega) is used as a parameter for measuring the reliability of the evaluation process of the evaluator, and the calculation process is as follows:
first, the arithmetic mean of the evaluation index grades of the emergency plan is calculated according to the following formula
Then, the difference (d) between the j-th index grade and the sum of the evaluation index grades of the emergency plan is calculated according to the following formulaj);
Finally, a classification discussion is typically performed when calculating ω:
(1) when the evaluation personnel do not have the same rating, the omega is Kendall harmony coefficient, and the calculation formula is as follows:
(2) when the ratings rated by the evaluators have the same rating, ω must be corrected, which is calculated as follows:
in the above formulas, SjA rank representing the jth index; m represents the number of indexes to be evaluated, and n represents the number of evaluators; t isiRepresents the same level index in the evaluation index system, l represents the same evaluation group for evaluation of the index in the ith evaluator evaluation; t is tiIndicating that the evaluation groups have the same number of levels.
When the calculation results in omegaAnd then, the significance of omega can be checked in a table look-up mode, and the conclusion that whether the scores of all the evaluators for all the indexes are consistent is obtained. If the consistency is not achieved, the evaluator is required to conduct further discussion and conduct evaluation again until the results are consistent. After reaching consistency, calculating corresponding average number (M) according to the evaluation result of each evaluatorj) Full scale frequency (K)j) And coefficient of variation (V)j) The evaluation indexes of the emergency plan can be effectively screened.
Wherein, average number (M)j) Full scale frequency (K)j) And coefficient of variation (V)j) The calculation formula of (a) is as follows:
Kj=n/N
Vj=δj/Mj
in the above formula, CijThe score of the ith evaluator on the jth index is represented; n represents the number of people who obtain full points according to the j-th emergency plan evaluation index, and the number of people is considered to be full points if the evaluation score is set to be more than or equal to 9 in the embodiment; n represents the total number of evaluators; deltajThe standard deviation of the j-th index is shown.
In the result calculated in the above manner, MjThe larger the value is, the more important the j emergency plan evaluation index is; kjThe larger the value is, the more important the j emergency plan evaluation index is; vjThe larger the index is, the stronger the opinion consistency of each appraiser is, and the index can be selected. Based on this, screening can be performed according to a set threshold value, and finally an emergency plan evaluation index system as shown in fig. 3 is obtained.
Based on each evaluation index in the emergency plan evaluation index system, evaluation is performed by related evaluators according to the cloud evaluation scale in table 7.
TABLE 7 cloud evaluation Scale
Based on the evaluation of each evaluator, in the domain of discourse [ X ]min,Xmax]In the above, an emergency plan evaluation scheme decision cloud matrix is established in a scaling manner in table 7:
and S32, determining a decision attribute cloud parameter matrix of the emergency plan.
According to the evaluation weight of each evaluator, calculating the corresponding expected Ex, moisture En and super moisture He according to the following formulas:
wherein n represents the number of evaluators, ωiAnd represents the evaluation weight corresponding to the ith evaluator.
And then establishing a decision attribute cloud parameter matrix Y of the emergency plan according to the calculation result, wherein the decision attribute cloud parameter matrix Y is shown as the following formula:
wherein, Yij(Exij,Enij,Heij) (i ═ 1, 2, …, m; j ═ 1, 2, … n) represents the decision cloud parameters for attribute j in i of the emergency response.
And S33, determining the attribute weight of the emergency plan.
The method adopts a combined weighting algorithm of a network analytic hierarchy process and a grey correlation method based on a minimum deviation principle to weight each attribute of the emergency plan, and specifically comprises the following steps:
s331, calculating subjective weight by adopting network analytic hierarchy process (ANP):
(1) establishing ANP model
And constructing an ANP network model according to the endogenous relation among the emergency plan evaluation indexes obtained in the step S31.
(2) Constructing a supermatrix
Constructing a hypermatrix according to the mutual influence among the elements in the element set of the emergency plan evaluation index, wherein the hypermatrix is shown as the following formula:
wherein, WijAnd each column vector in the super matrix W is a characteristic vector of a judgment matrix obtained after comparison and judgment are carried out by taking one risk evaluation index as a criterion.
(3) Constructing a weighted supermtrix
For ease of calculation, each column of the super-matrix needs to be normalized by the following weighting matrix. The weighting matrix is denoted as A, A ═ aij),aij∈[0,1]And is and
(4) Calculating a limit supermatrix
After the weighted super matrix in the emergency plan evaluation index layer is obtained, the weighted super matrix is calculated by using the following formula to obtainExtreme over-matrix W∞Therefore, the importance degree sequence of the evaluation indexes of the emergency plans of the engineering construction projects is obtained.
When in useIn the presence of a limit of k → ∞ W∞Is a limit supermatrix. If the limit is convergent and unique, then W∞The jth column of (1) is the subjective weight of each index by relatively sorting the limits of each index.
In this embodiment, the comparison and judgment between the evaluation indexes of the emergency plans are performed by using an expert scoring method. And obtaining the subjective weight value of each index according to the comparison result obtained by an expert scoring method and the calculation mode.
S332, determining a mother index according to the subjective weight calculation result obtained in the step S331, and calculating objective weight according to a grey correlation analysis method:
establishing a reference sequence according to the subjective weight of each index obtained in the step S331 and taking the index with the maximum subjective weight as a parent index, and recording the reference sequence as the parent indexThe other indexes are used as sub-indexes to establish a comparison sequence which is recorded as
Then, the reference sequence and the comparison sequence are subjected to non-dimensionalization treatment, and the non-dimensionalized reference sequence is recorded as xj={xj(1),…,xj(n) the comparison number after the dimensionless processing is listed as xi={xi(1),…,xi(n)}。
Then, according to the following formula, the correlation coefficient xi of the risk evaluation index is calculatedi(k) And (3) calculating:
where ρ represents a resolution factor of the emergency plan evaluation index, and in the present embodiment, ρ is 0.5.
According to the calculated correlation coefficient xii(k) Then, the relevance r of the i-th risk evaluation index is calculated according to the following formulaiAnd objective weight ωiAnd (3) calculating:
wherein r isiAnd ωiRespectively representing the relevance and the objective weight of the evaluation index of the ith emergency plan.
In the present embodiment, the above calculation process is performed based on MATLABR2010 b.
S333, constructing a minimum deviation principle-based combined weight model, and performing combined calculation on the subjective weight obtained in the step S331 and the objective weight obtained in the step S332 to obtain a combined weight:
through the steps S331 and S332, not only can the relevance among the risk evaluation indexes be fully considered, but also the parent indexes can be selected according to the subjective weight, and objective weight calculation can be carried out, so that the subjective and objective calculation methods are effectively combined, the problem that the objective calculation is too rational is solved while the evaluation personnel are prevented from judging too subjective. On this basis, in order to reduce the deviation of weight calculation and further improve the accuracy of combining weights, the present embodiment constructs a combining weight model based on minimum deviation as follows, and is expressed as: omegaij=(1-μ)ωia+μωig。
Wherein, ω isifThe combined weight of the ith index representing the evaluation index of the emergency plan; omegaiaSubjective weight of the ith index representing the evaluation index of the emergency plan; omegaigAn objective weight of an ith index representing an evaluation index of the emergency plan; mu meansThe objective weight of the emergency plan evaluation index accounts for the proportion of the combined weight.
Specifically, in order to solve the deviation of the weights of the subjective and objective algorithms, the embodiment constructs a combinatorial optimization model as follows:
wherein, ak、ajRespectively representing weight coefficients corresponding to the kth algorithm and the jth algorithm of the emergency plan evaluation index weight algorithm; u. ofki、ujiAnd respectively representing the weight values corresponding to the kth algorithm and the jth algorithm of the risk evaluation index weight algorithm.
Further constructing a Lagrange function corresponding to the emergency plan evaluation index weight on the basis of the combined optimization model, wherein the Lagrange function is shown as the following formula:
where λ represents the parameters introduced by the lagrangian function.
For (a) in the above Lagrangian function1,…,aqλ), the results are as follows:
according to the gram's law, the solution of the equation set formed by the above formula exists and is unique, that is, the weight coefficient corresponding to each weighting method is obtained as a ═ (a)1,…,aq)。
In this embodiment, two methods, i.e., q ═ 2, are used in common. Based on the calculation results of the subjective weight and the objective weight calculated in this embodiment, the final weight coefficient a ═ can be calculated as described above (a ═1,a2) I.e. the combination obtained by the present embodiment based on the principle of minimum deviationWeight ωij=a1ωia+a2ωig。
S34, calculating the positive ideal value A of the emergency plan according to the following formula+And a negative ideal value A-:
A+={Yj +(maxExij)};A-={Yj -(minExij)}
Wherein the content of the first and second substances,andand (4) taking an absolute ideal solution, namely, taking values of the optimal and worst states of the attribute elements of each alternative emergency plan theoretically.
S35, respectively calculating the weighted distance between each alternative emergency plan and the positive ideal value and the negative ideal value according to the following formulaAnd
s36, calculating the closeness Ti of each alternative coping plan according to the following formula:
wherein, Ti∈[0,1],TiThe larger the value is, the better the effect of the plan in treating the engineering construction safety accident is. Based on this, according to the proximity TiAnd sequencing the alternative coping plans, and outputting the alternative coping plan with the maximum closeness Ti as an optimal emergency plan.
Based on the mode, the single-factor short-term prediction is carried out by constructing the time series model, and the support vector machine model optimized by the particle swarm optimization algorithm is constructed to carry out multi-factor system prediction, so that a layered engineering construction project safety risk early warning model is formed, and the engineering construction project safety risk is comprehensively and effectively predicted and early warned; and extracting a corresponding alternative emergency plan according to the obtained early warning condition, and evaluating the alternative emergency plan by adopting a mode of fusing a cloud model and an ideal point method to obtain an optimal emergency scheme, so that an effective coping scheme is provided while efficient early warning is carried out on risks, and the requirement of practical application is met.
In some embodiments of the present invention, there is further provided an early warning system for engineering construction project safety risk, the early warning system including:
the data acquisition module is used for acquiring and transmitting monitoring data in real time;
the data processing module is used for processing abnormal data in the monitoring data acquired by the data acquisition module;
the data analysis module is used for establishing a safety risk early warning model of the engineering construction project and carrying out risk early warning on the data processed by the data processing module;
the plan generating module is used for extracting an alternative emergency plan according to the risk early warning result output by the data analyzing module and generating an optimal emergency plan by evaluating the alternative emergency plan;
the storage module is used for storing basic data of the engineering construction project and monitoring data acquired by the data acquisition module;
and the control module is used for controlling the operation of the system and managing the user information.
The data acquisition module comprises a wireless sensor network for acquiring monitoring data in real time and a data transmission unit based on an LoRa technology.
For specific limitations of the early warning system for the engineering construction project safety risk, reference may be made to the above limitations on the early warning method for the engineering construction project safety risk, which are not described herein again. All modules in the early warning system for the safety risk of the engineering construction project can be completely or partially realized through software, hardware and a combination thereof. The modules can be embedded in a hardware form or independent from a processor in the computer device, and can also be stored in a memory in the computer device in a software form, so that the processor can call and execute operations corresponding to the modules.
In summary, the invention provides an early warning method and system for engineering construction project safety risks. According to the early warning method, the interference of data with errors on a risk prediction process is avoided by acquiring and processing sample data of an engineering construction project, so that the sample data is accurate and reliable; on the basis, the single-factor short-term prediction is carried out by constructing a time sequence model, and the support vector machine model optimized by the particle swarm optimization algorithm is constructed to carry out multi-factor system prediction, so that a layered engineering construction project safety risk early warning model is formed, and the engineering construction project safety risk is comprehensively and effectively predicted and early warned; then, the corresponding alternative emergency plans are further extracted according to the obtained early warning condition, and the alternative emergency plans are evaluated in a mode of fusing a cloud model and an ideal point method to obtain an optimal emergency scheme, so that the risk is effectively early warned, and an effective coping scheme is provided to meet the requirements of practical application.
Although the present invention has been described in detail with reference to the preferred embodiments, it will be understood by those skilled in the art that various changes may be made and equivalents may be substituted for elements thereof without departing from the spirit and scope of the present invention.
Claims (10)
1. The early warning method for the safety risk of the engineering construction project is characterized by comprising the following steps:
s1, collecting sample data of the engineering construction project and processing the sample data;
s2, establishing a hierarchical engineering construction project safety risk early warning model, and performing risk prediction on the processed sample data obtained in the step S1; the risk prediction model comprises a time series model for single-factor short-term prediction and a support vector machine model which is used for multi-factor system prediction and optimized by a particle swarm optimization algorithm;
and S3, extracting an alternative emergency plan according to the conclusion obtained by the risk prediction in the step S2, and evaluating the alternative emergency plan to generate an optimal emergency plan.
2. The early warning method for the safety risk of the engineering construction project according to claim 1, characterized in that: in step S3, the candidate emergency plan is evaluated in a manner of fusing a cloud model and an ideal point method, and the evaluation process includes the following steps:
s31, constructing an evaluation index system of the emergency plan, and establishing an evaluation scheme decision matrix of the emergency plan;
s32, determining a decision attribute cloud parameter matrix of the emergency plan;
s33, determining the attribute weight of the emergency plan;
s34, determining a positive ideal value and a negative ideal value of the emergency plan;
s35, calculating the weighted distance between each alternative emergency plan and the positive ideal value and the negative ideal value;
and S36, calculating the closeness of each alternative coping plan, sequencing the alternative coping plans according to the closeness, and taking the alternative coping plan with the maximum closeness as an optimal emergency scheme.
3. The early warning method for the safety risk of the engineering construction project according to claim 2, characterized in that: in step S33, the attribute weight of the emergency plan is obtained by performing combined weighting using a network analytic hierarchy process and a gray correlation method based on the minimum deviation rule.
4. The early warning method for the safety risk of the engineering construction project according to any one of claims 1 to 3, wherein: in step S3, the alternative emergency plan is extracted based on a two-stage similarity algorithm, which includes first calculating feature attributes by using a local similarity algorithm, then respectively accumulating the feature attribute values of the current case and the historical cases in the emergency plan library by using an overall similarity algorithm to obtain overall similarities respectively corresponding to the historical cases, and using the historical cases corresponding to the overall similarities greater than a preset threshold as the alternative emergency plan.
5. The early warning method for the safety risk of the engineering construction project according to any one of claims 1 to 4, wherein: in step S1, the sample data includes monitoring data and safety risk assessment data for the engineering construction project.
6. The early warning method for the safety risk of the engineering construction project according to claim 5, characterized in that: in step S1, the processing on the monitoring data includes coarse error analysis on the monitoring data based on the improved grubbs criterion and interpolation processing on missing data in the monitoring data based on a cubic spline interpolation method; the processing of the security risk assessment data includes obtaining an expected value of the security risk assessment data.
7. The early warning method for the safety risk of the engineering construction project according to claim 6, characterized in that: in step S1, the gross error analysis includes the steps of:
s11, calculating the suspected maximum value and the suspected minimum value of the monitoring data, and acquiring a Grabbs criterion critical value;
s12, comparing the suspected maximum value, the suspected minimum value and the critical value, and identifying and eliminating abnormal data in the monitoring data;
and S13, repeating the steps S11-S12, and repeatedly identifying and eliminating the monitoring data until the monitoring data has no abnormal value.
8. The early warning method for the safety risk of the engineering construction project according to claim 5, characterized in that: in step S2, the time series model is an autoregressive moving average model, and is used for performing single-factor short-term prediction on the monitoring data processed in step S1; and the support vector machine model optimized by the particle swarm optimization algorithm is used for carrying out multi-factor system prediction on the safety risk evaluation data processed in the step S1.
9. An early warning system for safety risk of engineering construction projects, which is used for executing the early warning method of any one of claims 1 to 8, and comprises the following steps:
the data acquisition module is used for acquiring and transmitting monitoring data in real time;
the data processing module is used for processing abnormal data in the monitoring data acquired by the data acquisition module;
the data analysis module is used for establishing a safety risk early warning model of the engineering construction project and carrying out risk early warning on the data processed by the data processing module;
the plan generating module is used for extracting an alternative emergency plan according to the risk early warning result output by the data analyzing module and generating an optimal emergency plan by evaluating the alternative emergency plan;
the storage module is used for storing basic data of the engineering construction project and monitoring data acquired by the data acquisition module;
and the control module is used for controlling the operation of the system and managing the user information.
10. The early warning system of engineering construction project safety risk of claim 9, characterized in that: the data acquisition module comprises a wireless sensor network for acquiring monitoring data in real time and a data transmission unit based on an LoRa technology.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110810537.4A CN113627735A (en) | 2021-07-16 | 2021-07-16 | Early warning method and system for safety risk of engineering construction project |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110810537.4A CN113627735A (en) | 2021-07-16 | 2021-07-16 | Early warning method and system for safety risk of engineering construction project |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113627735A true CN113627735A (en) | 2021-11-09 |
Family
ID=78380152
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110810537.4A Pending CN113627735A (en) | 2021-07-16 | 2021-07-16 | Early warning method and system for safety risk of engineering construction project |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113627735A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114169598A (en) * | 2021-11-29 | 2022-03-11 | 国网福建省电力有限公司 | Power transmission and transformation project progress early warning method considering complex environment |
CN117114922A (en) * | 2023-10-24 | 2023-11-24 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
CN117273467A (en) * | 2023-11-17 | 2023-12-22 | 江苏麦维智能科技有限公司 | Multi-factor coupling-based industrial safety risk management and control method and system |
CN117391451A (en) * | 2023-11-07 | 2024-01-12 | 建龙西林钢铁有限公司 | Digital safety control system for steel |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102156710A (en) * | 2011-03-02 | 2011-08-17 | 上海大学 | Plant identification method based on cloud model and TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method |
CN107360147A (en) * | 2017-07-03 | 2017-11-17 | 武汉理工大学 | Public cloud credibility evaluation method and system based on TOPSIS and cloud model |
AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
-
2021
- 2021-07-16 CN CN202110810537.4A patent/CN113627735A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102156710A (en) * | 2011-03-02 | 2011-08-17 | 上海大学 | Plant identification method based on cloud model and TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) method |
CN107360147A (en) * | 2017-07-03 | 2017-11-17 | 武汉理工大学 | Public cloud credibility evaluation method and system based on TOPSIS and cloud model |
AU2020104000A4 (en) * | 2020-12-10 | 2021-02-18 | Guangxi University | Short-term Load Forecasting Method Based on TCN and IPSO-LSSVM Combined Model |
Non-Patent Citations (5)
Title |
---|
李存斌;庆格夫;冯霞;祁之强;: "基于云模型和改进TOPSIS法的电力设备状态检修控制策略", 华东电力, no. 02, pages 151 - 155 * |
王凯;胡怡婧;徐青;: "基于时间序列ARMA模式识别的基坑监测预警优化研究", 工业安全与环保, no. 07, pages 33 - 36 * |
罗圆;朱颖;张小强;姚令侃;: "基于变权理论的铁路选线方案评价模型", 铁道工程学报, no. 08 * |
谢世军;: "多层次模糊综合风险评价模型的水利工程项目风险分析评价", 黑龙江水利科技, no. 11 * |
赵元庆;侯得恒;: "建筑施工项目安全预警系统的仿真研究", 计算机仿真, no. 02, pages 367 - 371 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114169598A (en) * | 2021-11-29 | 2022-03-11 | 国网福建省电力有限公司 | Power transmission and transformation project progress early warning method considering complex environment |
CN117114922A (en) * | 2023-10-24 | 2023-11-24 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
CN117114922B (en) * | 2023-10-24 | 2024-01-26 | 天津广正建设项目咨询股份有限公司 | Consultation service and evaluation method and system based on whole process engineering consultation |
CN117391451A (en) * | 2023-11-07 | 2024-01-12 | 建龙西林钢铁有限公司 | Digital safety control system for steel |
CN117273467A (en) * | 2023-11-17 | 2023-12-22 | 江苏麦维智能科技有限公司 | Multi-factor coupling-based industrial safety risk management and control method and system |
CN117273467B (en) * | 2023-11-17 | 2024-01-26 | 江苏麦维智能科技有限公司 | Multi-factor coupling-based industrial safety risk management and control method and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110223196B (en) | Anti-electricity-stealing analysis method based on typical industry feature library and anti-electricity-stealing sample library | |
CN113627735A (en) | Early warning method and system for safety risk of engineering construction project | |
CN110097297A (en) | A kind of various dimensions stealing situation Intellisense method, system, equipment and medium | |
CN110070282B (en) | Low-voltage transformer area line loss influence factor analysis method based on comprehensive relevance | |
CN107992968B (en) | Electric energy meter metering error prediction method based on integrated time series analysis technology | |
CN114548637A (en) | AHP-RST-based power communication backbone data network security comprehensive evaluation method | |
CN113762329A (en) | Method and system for constructing state prediction model of large rolling mill | |
CN116316599A (en) | Intelligent electricity load prediction method | |
CN108510180A (en) | The computational methods of performance interval residing for a kind of production equipment | |
CN114066196A (en) | Power grid investment strategy optimization system | |
CN110705859A (en) | PCA-self-organizing neural network-based method for evaluating running state of medium and low voltage distribution network | |
CN113869732A (en) | Scientific and technological project industrialization evaluation method based on factor analysis method | |
CN113642922A (en) | Small and medium-sized micro enterprise credit evaluation method and device | |
CN112949207A (en) | Short-term load prediction method based on improved least square support vector machine | |
CN112417627A (en) | Power distribution network operation reliability analysis method based on four-dimensional index system | |
CN114881374A (en) | Multi-element heterogeneous energy consumption data fusion method and system for building energy consumption prediction | |
CN112330030B (en) | System and method for predicting requirements of expansion materials | |
CN113627739A (en) | Construction method of engineering construction project safety risk evaluation index system | |
CN113837578A (en) | Gridding supervision and management evaluation method for power supervision enterprise | |
CN112950048A (en) | National higher education system health evaluation based on fuzzy comprehensive evaluation | |
CN112950067A (en) | Power consumer electricity utilization efficiency assessment method based on fuzzy comprehensive evaluation | |
CN117076691A (en) | Commodity resource knowledge graph algorithm model oriented to intelligent communities | |
CN115905319B (en) | Automatic identification method and system for abnormal electricity fees of massive users | |
Tanamal et al. | House price prediction model using random forest in surabaya city | |
CN116151799A (en) | BP neural network-based distribution line multi-working-condition fault rate rapid assessment method |
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 |