Remote monitoring and control method based on intelligent virtual engineering management system

Abstract

The present invention relates to the field of engineering management, and in particular to a remote monitoring and control method based on an intelligent virtual engineering management system. First, sensors are deployed at the engineering site to collect sensor data, and the data is mapped to a virtual engineering environment for virtualized data processing to obtain comprehensive data; an adaptive multi-dimensional anomaly detection algorithm is used to perform anomaly detection, and when the detection result is abnormal, feature extraction is performed on the comprehensive data, and the probability of the abnormal category is calculated based on the extracted feature vector; then, a multi-objective fuzzy control optimization algorithm is used to generate control instructions; by generating control instructions, the device status is remotely controlled. The problem that sensors are easily affected by noise and difficult to accurately reflect the actual situation; traditional anomaly detection methods have false alarms and missed alarms; after detecting anomalies, traditional methods are difficult to achieve automated and accurate control decisions, and are inefficient and error-prone.

Description

Technical Field

[0001] The present invention relates to the field of engineering management, and in particular to a remote monitoring and control method based on an intelligent virtual engineering management system. Background Art

[0002] With the rapid development of information technology and industrial automation, intelligent virtual engineering management systems have been widely used in modern engineering project management. Especially in large-scale and complex engineering projects, traditional intelligent virtual engineering management methods are often difficult to cope with dynamic changes and real-time requirements. The remote monitoring and control method based on the intelligent virtual engineering management system can achieve real-time monitoring and control of the engineering site through sensor networks, wireless communications, data acquisition and processing, and remote control to ensure that the engineering project proceeds smoothly as planned.

[0003] As an important tool for modern engineering management, the remote monitoring and control method based on the intelligent virtual engineering management system has broad application prospects and huge development potential. Through the comprehensive application of the Internet of Things, big data, cloud computing and artificial intelligence technologies, the remote monitoring and control method can achieve real-time monitoring and intelligent management of engineering projects, and improve the management efficiency and quality of projects. In the future, with the continuous advancement and innovation of technology, the intelligent virtual engineering management system will be further developed and improved, bringing changes and innovations to engineering management.

[0004] The traditional intelligent virtual engineering management methods have the following technical problems: when the environmental conditions at the engineering site are complex, sensor data is easily affected by noise and interference, resulting in unstable data and difficulty in accurately reflecting the actual situation; traditional anomaly detection methods have problems with false alarms and missed alarms, making it difficult to accurately detect abnormal conditions at the engineering site; after detecting anomalies, traditional methods are difficult to achieve automated and accurate control decisions, requiring manual intervention, being inefficient, and prone to errors. Summary of the invention

[0005] The present invention provides a remote monitoring and control method based on an intelligent virtual engineering management system to solve the following technical problems: in the case of complex environmental conditions at the engineering site, sensor data is easily affected by noise and interference, resulting in unstable data and difficulty in accurately reflecting the actual situation; traditional anomaly detection methods have false positives and missed positives, making it difficult to accurately detect abnormal conditions at the engineering site; after detecting an anomaly, traditional methods are difficult to achieve automated and accurate control decisions, require manual intervention, are inefficient, and are prone to errors.

[0006] The remote monitoring and control method based on the intelligent virtual engineering management system of the present invention specifically includes the following technical solutions:

[0007] The remote monitoring and control method based on the intelligent virtual engineering management system includes the following steps:

[0008] S1: Deploy sensors at the engineering site, collect sensor data, map the sensor data to the virtual engineering environment, perform virtualized data processing, and obtain comprehensive data in the virtual engineering environment;

[0009] S2: Anomaly detection is performed on the comprehensive data in the virtual engineering environment by using an adaptive multi-dimensional anomaly detection algorithm. When the anomaly detection result is abnormal, feature extraction is performed on the comprehensive data in the virtual engineering environment to obtain a feature vector. Based on the feature vector, the probability of the abnormal category is calculated;

[0010] S3: Generate control instructions using a multi-objective fuzzy control optimization algorithm based on the probability of the abnormal category; remotely control the device status by generating control instructions.

[0011] Preferably, the S1 specifically includes:

[0012] The sensor data is mapped into the virtual engineering environment using a virtualized data weighted correction integration algorithm.

[0013] Preferably, the S1 specifically includes:

[0014] The virtualized data weighted correction integration algorithm introduces sensor weights, environmental correction coefficients and coordination factors between sensors in the calculation process, and generates comprehensive data in a virtual engineering environment through weighted calculation and collaborative correction mechanism.

[0015] Preferably, the S2 specifically includes:

[0016] The adaptive multi-dimensional anomaly detection algorithm includes moving average calculation, time difference coefficient calculation and anomaly detection determination.

[0017] Preferably, the S2 specifically includes:

[0018] The time difference coefficient calculation involves two steps. The first step is to calculate the difference between the comprehensive data in the virtual engineering environment at two adjacent time points for each time interval. The second step is to weight the difference according to the attenuation parameter to obtain the time difference coefficient.

[0019] Preferably, the S2 specifically includes:

[0020] The anomaly detection judgment calculates the difference between the comprehensive data at the current time point in the virtual engineering environment and the moving average, and normalizes it according to the time difference coefficient. When the normalized difference value exceeds the anomaly detection threshold, there is an anomaly in the comprehensive data at the current time point in the virtual engineering environment.

[0021] Preferably, the S3 specifically includes:

[0022] By introducing fuzzy control theory and multi-objective optimization algorithm, a multi-objective fuzzy control optimization algorithm is constructed.

[0023] Preferably, the S3 specifically includes:

[0024] In the process of implementing the multi-objective fuzzy control optimization algorithm, a fuzzy rule base is established based on the actual situation of the engineering site, the abnormal category probabilities and the comprehensive data in the virtual engineering environment are mapped to fuzzy sets, and preliminary control instructions are generated through fuzzy reasoning; the preliminary control instructions are optimized through the multi-objective optimization algorithm.

[0025] The beneficial effects of the technical solution of the present invention are:

[0026] 1. Use the virtual data weighted correction integration algorithm to map the collected sensor data to the virtual engineering environment for virtual data processing to generate comprehensive data. Through weighted calculation and collaborative correction mechanism, ensure that the sensor data accurately reflects the actual situation, and assign different weights to the importance of each sensor data to solve the data deviation problem caused by differences between sensors. Finally, the high-precision integration of comprehensive data in the virtual engineering environment is achieved, providing a reliable data foundation for subsequent analysis;

[0027] 2. Anomaly detection is performed on the comprehensive data in the virtual engineering environment through an adaptive multi-dimensional anomaly detection algorithm to timely discover abnormal situations at the engineering site. The three core steps of moving average calculation, time difference coefficient calculation and anomaly detection judgment are adopted to improve the accuracy and robustness of anomaly detection. In particular, in the anomaly detection judgment process, the ability to identify abnormal data is significantly improved through normalization processing, thereby ensuring that the virtual engineering management system can quickly respond to and handle emergencies;

[0028] 3. Based on the results of anomaly detection, feature extraction is performed to obtain feature vectors, and a logistic regression model is used to classify anomalies and calculate the probability of anomaly categories. By performing feature extraction and logistic regression analysis on the comprehensive data in the virtual engineering environment, the anomaly category is accurately determined, which improves the accuracy of anomaly classification. Further analysis of abnormal data helps to determine the specific type and potential cause of the anomaly, thereby providing a basis for taking targeted control measures;

[0029] 4. According to the probability of abnormal categories, a multi-objective fuzzy control optimization algorithm is used to automatically generate precise control instructions. Through fuzzy reasoning and multi-objective optimization, a balance is achieved between multiple goals, efficiency, safety, and stability, and the best control instructions are generated, realizing intelligent adjustment of equipment on the engineering site to ensure rapid recovery to normal status or avoid further abnormalities. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 This is a flow chart of the remote monitoring and control method based on the intelligent virtual engineering management system described in the present invention. DETAILED DESCRIPTION

[0031] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the technical scheme in the embodiment of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiment of the present invention. Obviously, the described embodiment is only a part of the embodiment of the present invention, not all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0032] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0033] The specific scheme of the remote monitoring and control method based on the intelligent virtual engineering management system provided by the present invention is described in detail below with reference to the accompanying drawings.

[0034] See attached Figure 1 , which shows a flow chart of a remote monitoring and control method based on an intelligent virtual engineering management system provided by an embodiment of the present invention, the method comprising the following steps:

[0035] S1. Deploy sensors at the engineering site, collect sensor data, map the sensor data to the virtual engineering environment, perform virtualized data processing, and obtain comprehensive data in the virtual engineering environment.

[0036] Deploy sensors at key locations on the construction site, such as pressure sensors and equipment status sensors, to collect sensor data in real time.

[0037] The collected sensor data is mapped into the virtual engineering environment using a virtualized data weighted correction integration algorithm for virtualized data processing to obtain comprehensive data in the virtual engineering environment.

[0038] The virtualized data weighted correction integration algorithm generates comprehensive data in a virtual engineering environment through weighted calculation and collaborative correction mechanism, wherein each sensor data is assigned different weights according to its importance; in order to ensure accurate reflection of the actual situation, an environmental correction coefficient is introduced to adjust the sensor readings; in order to make the correction process smooth and reliable, a coordination factor between sensors is introduced to control the sensitivity of difference correction.

[0039] The specific formula for virtualized data processing is:

[0040] ,

[0041] in, Indicates the first Comprehensive data at each time point; Express The sensor data is summed; Indicates the virtual engineering environment The sensor in Data at a time point; Indicates The weight of the sensor reflects the The importance of individual sensor data in the integrated data in a virtual engineering environment; Represents the collaborative correction factor, which is used to correct the data of each sensor, comprehensively considering the environmental correction factor and the difference between sensors to ensure the accuracy of the comprehensive data; Indicates The environmental correction factor of each sensor is used to correct the error of sensor data caused by environmental factors such as temperature and humidity. The environmental correction factor is determined by the sensor specifications provided by the manufacturer; Indicates that except Sensors outside The difference of sensor data is summed; Indicates the virtual engineering environment and The sensor in The absolute difference of the data at each time point is used for synergistic correction; It represents the coordination factor between sensors and controls the sensitivity of collaborative correction. It can be set according to the specific implementation scenario and is not limited here.

[0042] S2. Perform anomaly detection on the comprehensive data in the virtual engineering environment by using an adaptive multi-dimensional anomaly detection algorithm. When the anomaly detection result is abnormal, perform feature extraction on the comprehensive data in the virtual engineering environment to obtain a feature vector. Based on the feature vector, calculate the probability of the abnormal category.

[0043] By using an adaptive multi-dimensional anomaly detection algorithm to detect anomalies in the comprehensive data in the virtual engineering environment, abnormal situations on the engineering site can be discovered in a timely manner to ensure that the virtual engineering management system can respond and process quickly;

[0044] The adaptive multi-dimensional anomaly detection algorithm includes three core steps: moving average calculation, time difference coefficient calculation and anomaly detection determination, so as to improve the accuracy and robustness of anomaly detection;

[0045] The moving average calculation defines a time window of fixed size, calculates the average value of the data in a period of time before the current time point, smoothes the fluctuation of the comprehensive data, and reduces the impact of noise;

[0046] The time difference coefficient calculation involves two steps. The first step is to calculate the difference between the comprehensive data in the virtual engineering environment at two adjacent time points for each time interval. The second step is to weight the difference according to the attenuation parameter to obtain the time difference coefficient. The time difference coefficient reflects the change trend of the time series data in different time intervals, and can help the adaptive multi-dimensional anomaly detection algorithm to identify data that significantly deviates from the normal fluctuation range.

[0047] The anomaly detection judgment is made by comparing the difference between the comprehensive data at the current time point in the virtual engineering environment and the moving average value, and performing normalization processing according to the time difference coefficient. If the difference value between the comprehensive data at the current time point in the virtual engineering environment and the moving average value after normalization exceeds the threshold value of anomaly detection, it is considered that the comprehensive data at the current time point in the virtual engineering environment is abnormal;

[0048] The specific formula for analyzing comprehensive data in a virtual engineering environment using an adaptive multi-dimensional anomaly detection algorithm is as follows:

[0049] ,

[0050] in, Indicates the virtual engineering environment An indicator of whether the comprehensive data at a time point is abnormal, 1 indicates abnormality and 0 indicates normality; Indicates the first Comprehensive data at each time point; is the difference value obtained after normalization; It represents the time difference coefficient. By squaring the time difference coefficient, the abnormal difference can be amplified and the accuracy of anomaly detection can be improved. Represents the summation symbol, indicating that Add the items together, represents the time difference order; Indicates the first Comprehensive data at each time point; Indicates the first Comprehensive data at each time point; Represents the attenuation parameter of each time difference, controlling the influence weight of different time intervals; Indicates the threshold for anomaly detection, which can be set according to the specific implementation scenario and is not limited here; Represents the moving average within the time window. The specific calculation formula is as follows:

[0051] ,

[0052] in, Indicates the size of the time window; Represents a specific time point in a time series; Indicates the first Comprehensive data at each time point;

[0053] If the abnormality detection result is abnormal, feature extraction is performed on the comprehensive data in the virtual engineering environment to obtain a feature vector. If the abnormality detection result is normal, monitoring is continued. The feature extraction method is a technical means well known to those skilled in the art and will not be described in detail here.

[0054] Based on the feature vector, the logistic regression model is used to classify the anomaly and calculate the probability of the anomaly category. The specific calculation formula is as follows:

[0055] ,

[0056] in, Indicates The time points are classified as The probability of class anomaly, i.e. the probability of the anomaly class; Indicates The feature vector of each time point; Indicates the logistic regression model for The feature weight vector of the class anomaly; Indicates the logistic regression model for The bias term of the class anomaly makes the output of the logistic regression model accurate and avoids overfitting; Represents the base of natural logarithms, used to construct Function, which maps the result of the linear combination to a probability range from 0 to 1; Indicates negative, which is used to convert the output of the logistic regression model into a probability value;

[0057] By further analyzing the abnormal data, the specific type and potential cause of the abnormality can be determined so that the virtual engineering management system can take targeted control measures to improve the stability and reliability of the virtual engineering management system.

[0058] S3. Generate control instructions using a multi-objective fuzzy control optimization algorithm based on the probability of the abnormal category; remotely control the device status by generating control instructions.

[0059] According to the probability of abnormal categories, a multi-objective fuzzy control optimization algorithm is used to automatically generate precise control instructions to ensure that the equipment on the project site can be adjusted in time to restore normal status or avoid further abnormalities;

[0060] The purpose of the multi-objective fuzzy control optimization algorithm is to achieve accurate control decisions; introduce fuzzy control theory and multi-objective optimization algorithm, establish a fuzzy rule base based on the actual situation of the engineering site, map the abnormal category probability and the comprehensive data in the virtual engineering environment to the fuzzy set, generate preliminary control instructions through fuzzy reasoning, and optimize the preliminary control instructions through the multi-objective optimization algorithm to ensure that the preliminary control instructions achieve a balance between multiple objectives, such as efficiency, safety, and stability. The specific calculation formula is:

[0061] ,

[0062] in, Indicates The control instruction vector at a time point; Represents the set of control variables that solve the objective function to the minimum value , each control variable corresponds to an adjustable parameter; Represents the weight parameter for adjusting the influence of abnormal category probability on control instruction optimization, balancing the influence of abnormal category probability on control instruction generation; Express Sum the abnormal categories and accumulate the impact of all abnormal categories; Indicates The time points are classified as The probability of class anomaly, i.e. the probability of the anomaly class; Indicates the first Comprehensive data at each time point; Indicates the first Time point The ideal comprehensive data value of the class anomaly is used as a reference target to guide the generation of control instructions; Indicates the first The comprehensive data at each time point are Time point The square of the error between the ideal synthetic data values ​​of the class anomaly; Represents the regularization parameter, which is used to control the balance in the optimization process to prevent overfitting or underfitting; represents the summation symbol, represents the number of control variables; Indicates control variables; Indicates The reference value of each control variable can be set according to the specific implementation scenario and is not limited here; Indicates The standard deviation of the control variables is used for normalization so that control variables of different dimensions can be compared and adjusted in the same optimization process.

[0063] By generating control instructions and remotely controlling the equipment status, intelligent management and control of the engineering site can be achieved, the automation level and management efficiency of the virtual engineering management system can be improved, and remote monitoring and control of the intelligent virtual engineering management system can be realized.

[0064] In summary, the remote monitoring and control method based on intelligent virtual engineering management system has been completed.

[0065] The order of the embodiments of the invention is for description only and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0066] The various embodiments in this specification are described in a progressive manner, and the same or similar parts between the various embodiments can be referenced to each other, and each embodiment focuses on the differences from other embodiments.

[0067] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that the technical solutions described in the above embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention, and should be included in the protection scope of the present invention.

Claims

1. A remote monitoring and control method based on an intelligent virtual engineering management system, characterized in that: The following steps are involved: S1: Deploy sensors at the engineering site, collect sensor data, and use the virtualized data weighted correction integration algorithm to map the sensor data to the virtual engineering environment for virtualized data processing. The virtualized data weighted correction integration algorithm introduces sensor weights, environmental correction coefficients, and coordination factors between sensors during the calculation process, and generates comprehensive data in the virtual engineering environment through weighted calculation and collaborative correction mechanism. The specific formula for virtualized data processing is: ， in, Indicates the first Comprehensive data at each time point; Express The sensor data is summed; Indicates the virtual engineering environment The sensor in Data at each time point; Indicates The weight of each sensor; represents the synergy correction factor; Indicates Environmental correction factor for each sensor; Indicates that except Sensors outside The difference of sensor data is summed; Indicates the virtual engineering environment and The sensor in The absolute difference of the data at each time point; represents the coordination factor between sensors; S2: Anomaly detection is performed on the comprehensive data in the virtual engineering environment by using an adaptive multi-dimensional anomaly detection algorithm. The specific implementation formula is: ， in, Indicates the virtual engineering environment An indicator of whether the comprehensive data at a time point is abnormal, 1 indicates abnormality and 0 indicates normality; Indicates the first Comprehensive data at each time point; is the difference value obtained after normalization; represents the time difference coefficient; represents the summation symbol; Indicates the first Comprehensive data at each time point; Indicates the first Comprehensive data at each time point; represents the decay parameter for each time difference; represents the threshold for anomaly detection; Represents the moving average within the time window; When the anomaly detection result is abnormal, the comprehensive data in the virtual engineering environment is extracted to obtain feature vectors. Based on the feature vectors, the logistic regression model is used to classify the anomalies and calculate the probability of the anomaly category. The specific calculation formula is: ， in, Indicates The time points are classified as The probability of class anomaly, i.e. the probability of the anomaly class; Indicates The feature vector of each time point; Indicates the logistic regression model for The feature weight vector of the class anomaly; Indicates the logistic regression model for Bias term for abnormal class; represents the base of natural logarithms; It means taking negative; S3: Generate control instructions using a multi-objective fuzzy control optimization algorithm based on the probability of the abnormal category; remotely control the device status by generating control instructions.

2. The remote monitoring and control method based on intelligent virtual engineering management system according to claim 1 is characterized in that: In said S2, it specifically includes: The adaptive multi-dimensional anomaly detection algorithm includes moving average calculation, time difference coefficient calculation and anomaly detection determination.

3. The remote monitoring and control method based on intelligent virtual engineering management system according to claim 2 is characterized in that: In said S2, it specifically includes: The time difference coefficient calculation involves two steps. The first step is to calculate the difference between the comprehensive data in the virtual engineering environment at two adjacent time points for each time interval. The second step is to weight the difference according to the attenuation parameter to obtain the time difference coefficient.

4. The remote monitoring and control method based on intelligent virtual engineering management system according to claim 2 is characterized in that: In said S2, it specifically includes: The anomaly detection judgment calculates the difference between the comprehensive data at the current time point in the virtual engineering environment and the moving average, and normalizes it according to the time difference coefficient. When the normalized difference value exceeds the anomaly detection threshold, there is an anomaly in the comprehensive data at the current time point in the virtual engineering environment.

5. The remote monitoring and control method based on intelligent virtual engineering management system according to claim 1 is characterized in that: In said S3, it specifically includes: By introducing fuzzy control theory and multi-objective optimization algorithm, a multi-objective fuzzy control optimization algorithm is constructed.

6. The remote monitoring and control method based on intelligent virtual engineering management system according to claim 5 is characterized in that: In said S3, it specifically includes: In the process of implementing the multi-objective fuzzy control optimization algorithm, a fuzzy rule base is established based on the actual situation of the engineering site, the abnormal category probability and the comprehensive data in the virtual engineering environment are mapped to the fuzzy set, and the preliminary control instructions are generated through fuzzy reasoning; the preliminary control instructions are optimized through the multi-objective optimization algorithm, and the specific calculation formula is: ， in, Indicates The control instruction vector at a time point; Represents the set of control variables that solve the objective function to the minimum value ; The weight parameter representing the effect of adjusting the probability of abnormal categories on the optimization of control instructions; Express The anomaly categories are summed; Indicates The time points are classified as The probability of class anomaly, i.e. the probability of the anomaly class; Indicates the first Comprehensive data at each time point; Indicates the first Time point Ideal comprehensive data value for class anomalies; represents the regularization parameter; represents the summation symbol, represents the number of control variables; Indicates control variables; Indicates reference values ​​of the control variables; Indicates The standard deviation of the control variables.

Images