MR virtual visualization space safety supervision system based on electric power

Abstract

The invention relates to the technical field of electric power, in particular to an MR virtual visualization space safety supervision system based on electric power, which comprises a cloud management platform, a component displacement deformation judgment module, a component real-time monitoring module, an electric power data comprehensive detection module, an electric power data supervision module, an early warning module, a three-dimensional data visualization module and an MR glasses client. According to the invention, component deformation displacement analysis is carried out on corresponding components in the power device through the component displacement deformation judgment module, and the to-be-analyzed component is monitored in real time and the operation risk condition of the to-be-analyzed component is judged through the component real-time monitoring module, so that safe operation of all the components in the power device is effectively ensured; and the potential safety hazard during the operation of the power device is obviously reduced.

Description

Technical Field

[0001] The present invention relates to the field of electric power technology, and more specifically to an MR virtual visualization space safety supervision system based on electric power. Background Art

[0002] The power-based MR virtual visualization space safety supervision system is an innovative technical solution that combines power monitoring, mixed reality technology and advanced concepts of safety supervision, aiming to improve the safety, efficiency and intelligence level of the power industry.

[0003] The power MR virtual visualization space safety supervision system constructs a three-dimensional virtual environment to present the real-time operating status, environmental parameters and safety monitoring information of power devices to operation and maintenance personnel in an intuitive and interactive way. Various faults may occur during the operation of power devices. If they are not discovered and handled in time, they are likely to cause safety accidents. Therefore, it is necessary to detect the operation process of power devices;

[0004] The patent application with reference publication number CN116258475A discloses a remote operation and maintenance system and method for fracturing equipment based on digital twin and MR visualization environment. The fracturing equipment sensor collects real-time equipment operation data, which is processed by the logic controller PLC and then uploaded to the Internet cloud platform through the Internet of Things gateway. The present invention comprehensively monitors and analyzes the operating parameters of the fracturing field operation equipment, establishes a three-dimensional data model of the digital twin of the fracturing equipment, and quickly realizes comparative analysis of the real-time operation data of the fracturing field operation equipment through data fusion and big data analysis, so as to achieve the goal of fine-grained use and supervision of data by the operation and maintenance business, and improve the intelligence level of the remote operation and maintenance system; through the MR glasses client, the physical space and digital space data information are integrated, and audio and video communication with remote experts from the first-person perspective is established, so as to achieve efficient remote collaboration and work guidance, solve the faults of the fracturing field operation equipment, reduce human errors and improve work safety and timeliness;

[0005] However, when detecting the operation process of the power device, the existing technology is unable to make a reasonable judgment on the displacement and deformation risks of the corresponding components in the power device, is unable to accurately assess its real-time safety hazard status, and is unable to identify the power anomalies of the power device and make corresponding management and control operations. It is unable to achieve effective operation and maintenance supervision and intelligent control of the power device during operation, and cannot ensure the safe and stable operation of the power device.

[0006] To this end, we propose an electricity-based MR virtual visualization space safety supervision system to address the above issues. Summary of the invention

[0007] The purpose of the present invention is to provide an MR virtual visualization space safety supervision system based on electricity, which solves the problem that the prior art is unable to reasonably judge the displacement deformation risk of corresponding components in the power device, cannot accurately assess its real-time safety hazard status, and cannot identify power anomalies of the power device and make corresponding management and control operations, which is not conducive to ensuring the safe and stable operation of the power device.

[0008] The purpose of the present invention can be achieved through the following technical solutions:

[0009] The MR virtual visualization space safety supervision system based on electricity includes a cloud management platform, a component displacement and deformation determination module, a component real-time monitoring module, a power data comprehensive inspection module, a power data supervision module, an early warning module, a three-dimensional data visualization module and an MR glasses client;

[0010] The component displacement and deformation determination module performs component deformation and displacement analysis on the target component m;

[0011] Component real-time monitoring module, which monitors the components to be analyzed in real time;

[0012] The early warning module receives components to be inspected, component high-risk signals, regulatory abnormality warning information, and regulatory high-risk signals, and issues corresponding early warning information respectively;

[0013] The power data comprehensive inspection module processes and analyzes the collected power data;

[0014] The power data supervision module performs corresponding supervision operations on the power device when receiving abnormal information;

[0015] The three-dimensional data visualization module uses 3D software to integrate the three-dimensional model of the power device with the high-realistic simulation environment, displays the collected real-time data at the corresponding position of the three-dimensional model, generates a three-dimensional virtual image of the power device, and sends the three-dimensional virtual image of the power device to the cloud management platform;

[0016] MR glasses client, obtains three-dimensional virtual images of power devices and corresponding warning information.

[0017] As a preferred embodiment of the present invention, the specific analysis process of component deformation displacement analysis is as follows:

[0018] The component displacement measurement value is obtained, which represents the deviation distance between the standard position set by the target component m and the actual position. The component displacement measurement value is marked as ZWC. The target component m represents the component to be monitored in the power device, and m is a natural number greater than 1. The component displacement growth value of the target component m per unit time is collected, and the component displacement growth value is marked as ZWZ. Through the formula Obtain the component displacement risk value, where b1 and b2 are preset proportional coefficients, b2>b1>0, and compare and analyze the component displacement risk value ZWF with the preset component displacement risk value threshold value recorded and stored internally;

[0019] If the component displacement risk value ZWF is greater than the preset component displacement risk value threshold, the target component m is marked as a component to be inspected, and the component to be inspected is sent to the early warning module via the cloud management platform. When the early warning module receives the component to be inspected, it issues a corresponding early warning message.

[0020] As a preferred embodiment of the present invention, if the component displacement risk value ZWF is less than or equal to the preset component displacement risk value threshold, a number of checkpoints are set on the target component m, and the deviation value between the actual distance value between any two checkpoints and the preset distance value is marked as the point distance deviation value;

[0021] If the point distance deviation value is greater than the preset point distance deviation value threshold, the corresponding point distance deviation value will be marked as a point distance anomaly value, and the ratio of the number of point distance anomaly values ​​to the number of point distance deviation values ​​will be calculated to obtain the point distance anomaly ratio value, which will be marked as DYZ. All point distance deviation values ​​will be summed up and averaged to obtain the point distance deviation mean, which will be marked as DPJ.

[0022] As a preferred embodiment of the present invention, the point distance abnormality ratio value marked as DYZ and the point distance deviation mean DPJ are obtained, and the component deformation risk value is obtained by the formula ZXF=c1*DYZ+c2*DPJ, wherein c1 and c2 are preset weight coefficients, c1>c2>0, and the component deformation risk value ZXF is compared and analyzed with the preset component deformation risk value threshold value recorded and stored internally;

[0023] If the component deformation risk value ZXF is greater than the preset component deformation risk value threshold, the target component m is marked as a component to be inspected;

[0024] If the component deformation risk value ZXF is less than or equal to the preset component deformation risk value threshold, the target component m is marked as a component to be analyzed, and the component to be analyzed is sent to the component real-time monitoring module via the cloud management platform.

[0025] As a preferred embodiment of the present invention, the specific analysis process of component real-time monitoring and analysis is as follows:

[0026] The real-time vibration frequency and real-time vibration amplitude of the corresponding component to be analyzed are collected, and the real-time vibration frequency and the real-time vibration amplitude are summed to obtain a real-time vibration value, which is marked as SZ;

[0027] The real-time humidity and real-time smoke concentration of the environment in which the corresponding component to be analyzed is collected, the real-time humidity is compared with the median of the preset suitable humidity range, and the absolute value is taken to obtain the real-time humidity difference, and the real-time smoke concentration and the real-time humidity difference are marked as SYN and SSC respectively, and the real-time temperature of the corresponding component to be analyzed is collected, the real-time temperature is compared with the median of the corresponding preset suitable temperature range, and the absolute value is taken to obtain the real-time temperature difference, and the real-time temperature difference is marked as SWC.

[0028] As a preferred embodiment of the present invention, the real-time vibration value SZ, the real-time smoke concentration SYN, the real-time humidity difference SSC and the real-time temperature difference SWC are obtained;

[0029] By formula Obtain the monitoring and assessment value, where e1, e2, e3, and e4 are preset proportional coefficients, and the values ​​of e1, e2, e3, and e4 are all positive numbers, and compare and analyze the monitoring and assessment value JP with the preset monitoring and assessment value threshold value entered and stored internally;

[0030] If the monitoring assessment value JP is greater than the preset monitoring assessment value threshold, it is determined that the corresponding component to be analyzed is in a monitoring abnormal state.

[0031] As a preferred embodiment of the present invention, the specific operation process of the component real-time monitoring module is as follows:

[0032] The total duration of the component to be analyzed corresponding to the detection period in the monitoring abnormal state is collected and marked as the total abnormal duration value YZS, and the maximum single duration of the component to be analyzed corresponding to the detection period in the monitoring abnormal state is collected and marked as the maximum single abnormal duration DZS, and all monitoring evaluation values ​​of the component to be analyzed corresponding to the detection period are summed and averaged to obtain the monitoring evaluation value mean, and the monitoring evaluation value mean is marked as JPJ;

[0033] By formula Obtaining a component evaluation value, wherein d1, d2, and d3 are preset proportional coefficients, and the values ​​of d1, d2, and d3 are all greater than zero, and comparing and analyzing the component evaluation value ZP with the preset component evaluation value threshold value stored internally;

[0034] If the component assessment value ZP is greater than the preset component assessment value threshold, a component high-risk signal corresponding to the component to be analyzed is generated, and the component high-risk signal and the corresponding component to be analyzed are sent to the early warning module via the cloud management platform;

[0035] If the component assessment value ZP is less than or equal to the preset component assessment value threshold, a component low risk signal corresponding to the component to be analyzed is generated.

[0036] As a preferred embodiment of the present invention, the specific process of the power data comprehensive inspection module processing and analyzing the power data is as follows:

[0037] Data preprocessing: preprocess the collected power data;

[0038] Feature extraction: extracting features related to the power operation status from the preprocessed data;

[0039] Abnormal identification and detection: Based on the extracted features and using classification algorithms or machine learning algorithms, the operating status of the power device is identified, and the actual power data is compared with the corresponding normal range or threshold one by one to determine whether the power device has power abnormalities;

[0040] Information extraction: Extract abnormal information of power devices based on the results of abnormal identification and detection;

[0041] Result output: The extracted abnormal information is sent to the power data supervision module and early warning module via the cloud management platform.

[0042] As a preferred embodiment of the present invention, the cloud management platform is in communication connection with the supervision alarm generation module, and the supervision alarm generation module is used to collect the time point when the power data supervision module receives the corresponding abnormal information and the time point when the supervision operation is started when the power data supervision module performs the corresponding supervision operation on the power device, and mark them as the information sending time point and the instruction feedback time point respectively, and calculate the time difference between the instruction feedback time point and the information sending time point to obtain the supervision effectiveness value;

[0043] The timing starts from the time when the information is sent to obtain the supervision and adjustment duration; if the supervision and adjustment duration reaches the corresponding preset duration value threshold and the power data supervision module fails to successfully complete the regulation of the power device, a supervision abnormality alarm information is generated, and the supervision abnormality alarm information is sent to the early warning module via the cloud management platform. The early warning module displays the supervision abnormality alarm information and issues corresponding early warning information.

[0044] As a preferred implementation of the present invention, a supervision cycle is set, the number of times supervision abnormality alarm information is generated within the supervision cycle is collected and marked as the supervision abnormality frequency value GYP, and all supervision effective values ​​within the supervision cycle are summed and averaged to obtain the supervision risk value GF, and the supervision abnormality frequency value is calculated by the ratio of the number of times the power data supervision module receives abnormal information within the supervision cycle to obtain the supervision abnormality frequency ratio value GYZ, through the formula Obtain the regulatory warning value, where f1, f2, and f3 are preset proportional coefficients, and the values ​​of f1, f2, and f3 are all greater than zero, and compare and analyze the regulatory warning value GY with the preset regulatory warning value threshold value entered and stored internally;

[0045] If the regulatory warning value GY is greater than the preset regulatory warning value threshold, a high-risk regulatory signal is generated and sent to the warning module via the cloud management platform. When the warning module receives the high-risk regulatory signal, it issues a corresponding warning message.

[0046] Compared with the prior art, the advantages of the present invention are:

[0047] (1) In the present invention, the component displacement and deformation determination module is used to analyze the component deformation and displacement of the corresponding components in the power device, and the component real-time monitoring module is used to monitor the components to be analyzed in real time and judge their operating risk status, thereby effectively ensuring the safe operation of all components in the power device and significantly reducing the safety hazards during the operation of the power device;

[0048] (2) In the present invention, the power data of the power device is collected in real time through the power data comprehensive inspection module and processed and analyzed to determine whether there is a power anomaly. If there is a power anomaly, the power device is controlled accordingly to achieve effective operation and maintenance supervision and intelligent control of the power device during operation, thereby ensuring the safe and stable operation of the power device;

[0049] (3) In the present invention, the collected real-time data is displayed at the corresponding position of the power device through the three-dimensional data visualization module, and is displayed in the MR glasses client of the operation and maintenance personnel, so that the operation and maintenance personnel can fully understand the operating status of the device without going to the site in person, reducing the time and cost of on-site inspections. When an abnormal situation is found, the early warning module will send the corresponding early warning information to the MR glasses client, and can provide scientific disposal suggestions to the operation and maintenance personnel through remote guidance or data retrieval, so as to perform accurate maintenance processing on the corresponding position of the power device. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] Figure 1 This is a system block diagram of Embodiment 1 of the present invention;

[0051] Figure 2 This is a system block diagram of Embodiment 2 of the present invention;

[0052] Figure 3 It is a logical flow diagram of the present invention. DETAILED DESCRIPTION

[0053] The following will combine the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all the embodiments. All other embodiments obtained by ordinary technicians in this field without creative work based on the embodiments of the present invention belong to the scope of protection of the present invention.

[0054] Embodiment 1:

[0055] like Figure 1 As shown, the MR virtual visualization space safety supervision system based on electricity proposed by the present invention includes a cloud management platform, a component displacement deformation determination module, a component real-time monitoring module, a power data comprehensive inspection module, a power data supervision module, an early warning module, a three-dimensional data visualization module and an MR glasses client. The cloud management platform is connected to the power data supervision module, the component displacement deformation determination module, the power data comprehensive inspection module, the early warning module and the MR glasses client in a one-way communication manner, the cloud management platform is connected to the component real-time monitoring module and the three-dimensional data visualization module in a two-way communication manner, and the early warning module is connected to the MR glasses client in a one-way communication manner;

[0056] The component displacement and deformation determination module performs component deformation and displacement analysis on the target component m. The specific analysis process of component deformation and displacement analysis is as follows:

[0057] The component displacement measurement value is obtained, which represents the deviation distance between the standard position set by the target component m and the actual position. The component displacement measurement value is marked as ZWC. The target component m represents the component to be monitored in the power device, and m is a natural number greater than 1. The component displacement growth value of the target component m per unit time is collected, and the component displacement growth value is marked as ZWZ. Through the formula Obtain the component displacement risk value, where b1 and b2 are preset proportional coefficients, b2>b1>0, and compare and analyze the component displacement risk value ZWF with the preset component displacement risk value threshold value recorded and stored internally;

[0058] If the component displacement risk value ZWF is greater than the preset component displacement risk value threshold, it indicates that the displacement risk of the target component m is relatively large, and the potential safety hazard it brings is relatively large. Then the target component m is marked as a component to be inspected, and the component to be inspected is sent to the early warning module via the cloud management platform. When the early warning module receives the component to be inspected, it issues a corresponding early warning message, and the operation and maintenance personnel promptly inspect the component to be inspected to eliminate the potential safety hazard.

[0059] If the component displacement risk value ZWF is less than or equal to the preset component displacement risk value threshold, indicating that the displacement risk of the target component m is small, several checkpoints are set on the target component m, and the deviation value between the actual distance value and the preset distance value between any two checkpoints is marked as the point distance deviation value; if the point distance deviation value is greater than the preset point distance deviation value threshold, the corresponding point distance deviation value is marked as a point distance anomaly value, and the number of point distance anomaly values ​​is calculated by ratio with the number of point distance deviation values ​​to obtain the point distance anomaly ratio value, and the point distance anomaly ratio value is marked as DY Z; sum and calculate all point distance deviation values ​​and take the average to obtain the point distance deviation mean, mark the point distance deviation mean as DPJ, and obtain the component deformation risk value through the formula ZXF=c1*DYZ+c2*DPJ, where c1 and c2 are preset weight coefficients, c1>c2>0, and the larger the value of the component deformation risk value ZXF is, the more serious the deformation condition of the target component m is, and the greater the safety hazard is. The component deformation risk value ZXF is compared and analyzed with the preset component deformation risk value threshold value stored in the internal input;

[0060] If the component deformation risk value ZXF is greater than the preset component deformation risk value threshold, it indicates that the deformation condition of the target component m is serious and the potential safety hazard is great, then the target component m is marked as a component to be inspected;

[0061] If the component deformation risk value ZXF is less than or equal to the preset component deformation risk value threshold, it indicates that the deformation condition of the target component m is good and the potential safety hazard is small. Then the target component m is marked as a component to be analyzed and sent to the component real-time monitoring module via the cloud management platform.

[0062] The component real-time monitoring module performs real-time monitoring on the components to be analyzed. The specific analysis process of component real-time monitoring and analysis is as follows:

[0063] The real-time temperature of the corresponding component to be analyzed is collected, and the difference between the real-time temperature and the median of the corresponding preset suitable temperature range is calculated and the absolute value is taken to obtain the real-time temperature difference, and the real-time temperature difference is marked as SWC; and the real-time humidity and real-time smoke concentration of the environment in which the corresponding component to be analyzed is collected, and the real-time humidity is compared with the median of the preset suitable humidity range. The difference is calculated and the absolute value is taken to obtain the real-time humidity difference, and the real-time smoke concentration and the real-time humidity difference are marked as SYN and SSC, respectively; and the real-time vibration frequency and real-time vibration amplitude of the corresponding component to be analyzed are collected, and the real-time vibration frequency and the real-time vibration amplitude are summed to obtain the real-time vibration value, and the real-time vibration value is marked as SZ; through the formula The monitoring and assessment value is obtained, wherein e1, e2, e3, and e4 are preset proportional coefficients, and the values ​​of e1, e2, e3, and e4 are all positive numbers. The larger the value of the monitoring and assessment value JP is, the greater the operating risk of the corresponding component to be analyzed at the corresponding moment is, and the monitoring and assessment value JP is compared and analyzed with the preset monitoring and assessment value threshold value stored in the internal input;

[0064] If the monitoring assessment value JP is greater than the preset monitoring assessment value threshold, it indicates that the operation risk of the corresponding component to be analyzed at the corresponding moment is relatively high, and the corresponding component to be analyzed is judged to be in a monitoring abnormal state;

[0065] The specific operation process of the component real-time monitoring module is as follows:

[0066] The total duration of the component to be analyzed corresponding to the detection period in the monitoring abnormal state is collected and marked as the total abnormal duration value YZS, and the maximum single duration of the component to be analyzed corresponding to the detection period in the monitoring abnormal state is collected and marked as the maximum single abnormal duration DZS, and all monitoring and evaluation values ​​of the component to be analyzed corresponding to the detection period are summed and averaged to obtain the monitoring and evaluation value mean, and the monitoring and evaluation value mean is marked as JPJ. It should be noted that the larger the values ​​of the total abnormal duration value, the maximum single abnormal duration value and the monitoring and evaluation value mean, the greater the safety hazard of the corresponding component to be analyzed in the detection period.

[0067] By formula Obtaining a component assessment value, wherein d1, d2, and d3 are preset proportional coefficients, and the values ​​of d1, d2, and d3 are all greater than zero. The larger the value of the component assessment value ZP is, the greater the safety hazard of the corresponding component to be analyzed during the detection period is. The component assessment value ZP is compared and analyzed with the preset component assessment value threshold value stored in the internal input;

[0068] If the component assessment value ZP is greater than the preset component assessment value threshold, it indicates that the corresponding component to be analyzed has a relatively large potential safety hazard during the detection period. Then, a component high-risk signal of the corresponding component to be analyzed is generated, and the component high-risk signal and the corresponding component to be analyzed are sent to the early warning module via the cloud management platform.

[0069] When the early warning module receives a high-risk signal from a component, it issues a corresponding early warning message. When the operation and maintenance personnel receive the corresponding early warning message, they promptly investigate the cause and inspect the components corresponding to the high-risk signal as needed, further ensuring the safe operation of all components and significantly reducing the potential safety hazards during the operation of the power device.

[0070] If the component assessment value ZP is less than or equal to the preset component assessment value threshold, it indicates that the safety hazard of the corresponding component to be analyzed during the detection period is relatively small, and a component low risk signal of the corresponding component to be analyzed is generated;

[0071] The power data comprehensive inspection module processes and analyzes the collected power data. The specific process of the power data comprehensive inspection module processing and analyzing the power data is as follows:

[0072] Data preprocessing: preprocess the collected power data, including data cleaning, filtering and denoising, to eliminate outliers, noise and errors in the original data and improve the accuracy and reliability of the data;

[0073] Feature extraction: Extract features related to the power operation status from the preprocessed data, such as voltage, current, etc. These features can reflect the operating status and performance of the equipment;

[0074] Abnormal identification and detection: Based on the extracted features, the operating status of the power device is identified using a classification algorithm or a machine learning algorithm. Common classification algorithms include support vector machines and neural networks. The actual power data is compared with the corresponding normal range or threshold one by one to determine whether the power device has power abnormalities. For example, if the actual data exceeds the normal range or threshold, it is considered that the device has power abnormalities.

[0075] Information extraction: Extract the abnormal information of the power device based on the results of abnormal identification and detection, where the abnormal information includes the abnormal type and occurrence time, etc.;

[0076] Result output: The extracted abnormal information is sent to the power data supervision module and early warning module via the cloud management platform;

[0077] When the power data supervision module receives abnormal information, it performs corresponding control operations on the power device to restore the corresponding power data status of the power device to normal. When the early warning module receives abnormal information, it issues a corresponding early warning so that the operation and maintenance personnel can grasp the operation status of the power device in detail and realize effective operation and maintenance supervision of the power device during operation.

[0078] The three-dimensional data visualization module uses 3D software to integrate the three-dimensional model of the power device with the high-realistic simulation environment, displays the collected real-time data at the corresponding position of the three-dimensional model, generates a three-dimensional virtual image of the power device, and sends the three-dimensional virtual image of the power device to the cloud management platform;

[0079] The MR glasses client obtains a three-dimensional virtual image of the power device, and the on-site real-time data of the power device is displayed at the corresponding position on the three-dimensional virtual image, so that the on-site operation and maintenance personnel can have an in-depth understanding of the operating status of the power device and perform corresponding maintenance and operation supervision on the power device according to the corresponding warning information sent by the warning module.

[0080] Embodiment 2: Figure 2 As shown, the technical solution of the embodiment of the present invention is different from that of the first embodiment in that:

[0081] The cloud management platform is in communication connection with the supervision alarm generation module. The supervision alarm generation module is used to collect the time point when the power data supervision module receives the corresponding abnormal information and the time point when the supervision operation is started when the power data supervision module performs the corresponding supervision operation on the power device, and mark them as the information sending time point and the instruction feedback time point respectively, and calculate the time difference between the instruction feedback time point and the information sending time point to obtain the supervision effectiveness value;

[0082] The timing starts from the time when the information is sent to obtain the supervision and adjustment duration; if the supervision and adjustment duration reaches the corresponding preset duration value threshold and the power data supervision module fails to successfully complete the regulation of the power device, a supervision abnormality alarm message is generated, and the supervision abnormality alarm message is sent to the early warning module via the cloud management platform. The early warning module displays the supervision abnormality alarm message and issues a corresponding early warning message;

[0083] And set a supervision cycle, preferably, the supervision cycle is five days, collect the number of times that supervision abnormality alarm information is generated within the supervision cycle and mark it as the supervision abnormality frequency value GYP, and sum and calculate all the supervision effective values ​​within the supervision cycle and take the average to obtain the supervision risk value GF, and calculate the ratio of the supervision abnormality frequency value to the number of times the power data supervision module receives abnormal information within the supervision cycle to obtain the supervision abnormality frequency ratio value GYZ. It should be noted that the larger the values ​​of the supervision abnormality frequency value, the supervision risk value and the supervision abnormality frequency ratio value, the greater the operation risk of the power device within the supervision cycle;

[0084] By formula Obtain the regulatory warning value, where f1, f2, and f3 are preset proportional coefficients, and the values ​​of f1, f2, and f3 are all greater than zero. The larger the value of the regulatory warning value HX, the greater the operating risk of the power device within the regulatory period, and the more it is necessary to strengthen the corresponding optimization and operation and maintenance supervision, and compare and analyze the regulatory warning value GY with the preset regulatory warning value threshold value stored in the internal input;

[0085] If the regulatory warning value GY is greater than the preset regulatory warning value threshold, indicating that the operation risk of the power device within the regulatory period is relatively high, a regulatory high-risk signal is generated, and the regulatory high-risk signal is sent to the warning module via the cloud management platform. When the warning module receives the regulatory high-risk signal, it issues a corresponding warning message so that the operation and maintenance personnel can promptly strengthen the operation and maintenance supervision and corresponding optimization of the power device, and further ensure the safe and stable operation of the power device;

[0086] The supervision alarm generation module analyzes the control process of the power data supervision module and determines whether to generate supervision abnormality alarm information. It also accurately evaluates the operating risk level of the power device during the supervision cycle to determine whether to generate a high-risk supervision signal, which is beneficial to ensuring the safe and stable operation of the power device.

[0087] The working principle of the present invention is as follows: when in use, the component displacement and deformation judgment module is used to analyze the component deformation and displacement of the corresponding components in the power device, and the component real-time monitoring module is used to monitor the components to be analyzed in real time and judge their operating risk status, thereby effectively ensuring the safe operation of all components in the power device and significantly reducing the potential safety hazards during the operation of the power device; and the power data of the power device is collected in real time through the power data comprehensive inspection module and processed and analyzed to determine whether there is a power anomaly. If there is a power anomaly, the power device is controlled and managed accordingly, thereby realizing effective operation and maintenance supervision and intelligent control of the power device during operation, and ensuring the safe and stable operation of the power device.

[0088] The above is only a preferred specific implementation manner of the present invention; but the protection scope of the present invention is not limited thereto; any technician familiar with the technical field within the technical scope disclosed by the present invention; any equivalent replacement or change based on the technical solution and improved concept of the present invention shall be covered by the protection scope of the present invention.

Claims

1. The MR virtual visualization space safety supervision system based on electricity is characterized by: It includes cloud management platform, component displacement and deformation determination module, component real-time monitoring module, power data comprehensive inspection module, power data supervision module, early warning module, three-dimensional data visualization module and MR glasses client; The component displacement and deformation determination module performs component deformation and displacement analysis on the target component m; Component real-time monitoring module, which monitors the components to be analyzed in real time; The early warning module receives components to be inspected, component high-risk signals, regulatory abnormality warning information, and regulatory high-risk signals, and issues corresponding early warning information respectively; The power data comprehensive inspection module processes and analyzes the collected power data; The power data supervision module performs corresponding supervision operations on the power device when receiving abnormal information; The three-dimensional data visualization module uses 3D software to integrate the three-dimensional model of the power device with the high-realistic simulation environment, displays the collected real-time data at the corresponding position of the three-dimensional model, generates a three-dimensional virtual image of the power device, and sends the three-dimensional virtual image of the power device to the cloud management platform; MR glasses client, obtains three-dimensional virtual images of power devices and corresponding warning information.

2. The power-based MR virtual visualization space safety supervision system according to claim 1 is characterized in that: The specific analysis process of component deformation displacement analysis is as follows: The component displacement measurement value is obtained, which represents the deviation distance between the standard position set by the target component m and the actual position. The component displacement measurement value is marked as ZWC. The target component m represents the component to be monitored in the power device, and m is a natural number greater than 1. The component displacement growth value of the target component m per unit time is collected, and the component displacement growth value is marked as ZWZ. Through the formula Obtain the component displacement risk value, where b1 and b2 are preset proportional coefficients, b2>b1>0, and compare and analyze the component displacement risk value ZWF with the preset component displacement risk value threshold value recorded and stored internally; If the component displacement risk value ZWF is greater than the preset component displacement risk value threshold, the target component m is marked as a component to be inspected, and the component to be inspected is sent to the early warning module via the cloud management platform. When the early warning module receives the component to be inspected, it issues a corresponding early warning message.

3. The power-based MR virtual visualization space safety supervision system according to claim 2 is characterized in that: If the component displacement risk value ZWF is less than or equal to the preset component displacement risk value threshold, several checkpoints are set on the target component m, and the deviation between the actual distance value and the preset distance value between any two checkpoints is marked as the point distance deviation value; If the point distance deviation value is greater than the preset point distance deviation value threshold, the corresponding point distance deviation value will be marked as a point distance anomaly value, and the point distance anomaly ratio value will be obtained by calculating the ratio of the number of point distance anomaly values ​​to the number of point distance deviation values. The point distance anomaly ratio value will be marked as DYZ, and all point distance deviation values ​​will be summed and averaged to obtain the point distance deviation mean value, which will be marked as DPJ.

4. The power-based MR virtual visualization space safety supervision system according to claim 3 is characterized in that: Obtain the point distance anomaly ratio value marked as DYZ and the point distance deviation mean value DPJ; The component deformation risk value is obtained by the formula ZXF=c1*DYZ+c2*DPJ, where c1 and c2 are preset weight coefficients, c1>c2>0, and the component deformation risk value ZXF is compared and analyzed with the preset component deformation risk value threshold value stored in the internal input; If the component deformation risk value ZXF is greater than the preset component deformation risk value threshold, the target component m is marked as a component to be inspected; If the component deformation risk value ZXF is less than or equal to the preset component deformation risk value threshold, the target component m is marked as a component to be analyzed, and the component to be analyzed is sent to the component real-time monitoring module via the cloud management platform.

5. The power-based MR virtual visualization space safety supervision system according to claim 1 is characterized in that: The specific analysis process of component real-time monitoring and analysis is as follows: The real-time vibration frequency and real-time vibration amplitude of the corresponding component to be analyzed are collected, and the real-time vibration frequency and the real-time vibration amplitude are summed to obtain a real-time vibration value, which is marked as SZ; The real-time humidity and real-time smoke concentration of the environment in which the corresponding component to be analyzed is collected, the real-time humidity is compared with the median of the preset suitable humidity range, and the absolute value is taken to obtain the real-time humidity difference, and the real-time smoke concentration and the real-time humidity difference are marked as SYN and SSC respectively, and the real-time temperature of the corresponding component to be analyzed is collected, the real-time temperature is compared with the median of the corresponding preset suitable temperature range, and the absolute value is taken to obtain the real-time temperature difference, and the real-time temperature difference is marked as SWC.

6. The power-based MR virtual visualization space safety supervision system according to claim 5 is characterized in that: Obtain the real-time vibration value SZ, real-time smoke concentration SYN, real-time humidity difference SSC and real-time temperature difference SWC; By formula Obtain the monitoring and assessment value, where e1, e2, e3, and e4 are preset proportional coefficients, and the values ​​of e1, e2, e3, and e4 are all positive numbers, and compare and analyze the monitoring and assessment value JP with the preset monitoring and assessment value threshold value entered and stored internally; If the monitoring assessment value JP is greater than the preset monitoring assessment value threshold, it is determined that the corresponding component to be analyzed is in a monitoring abnormal state.

7. The power-based MR virtual visualization space safety supervision system according to claim 6 is characterized in that: The specific operation process of the component real-time monitoring module is as follows: The total duration of the component to be analyzed corresponding to the detection period in the monitoring abnormal state is collected and marked as the total abnormal duration value YZS, and the maximum single duration of the component to be analyzed corresponding to the detection period in the monitoring abnormal state is collected and marked as the maximum single abnormal duration DZS, and all monitoring evaluation values ​​of the component to be analyzed corresponding to the detection period are summed and averaged to obtain the monitoring evaluation value mean, and the monitoring evaluation value mean is marked as JPJ; By formula Obtaining a component evaluation value, wherein d1, d2, and d3 are preset proportional coefficients, and the values ​​of d1, d2, and d3 are all greater than zero, and comparing and analyzing the component evaluation value ZP with the preset component evaluation value threshold value stored internally; If the component assessment value ZP is greater than the preset component assessment value threshold, a component high-risk signal corresponding to the component to be analyzed is generated, and the component high-risk signal and the corresponding component to be analyzed are sent to the early warning module via the cloud management platform; If the component assessment value ZP is less than or equal to the preset component assessment value threshold, a component low risk signal corresponding to the component to be analyzed is generated.

8. The power-based MR virtual visualization space safety supervision system according to claim 1 is characterized in that: The specific process of the power data comprehensive inspection module processing and analyzing power data is as follows: Data preprocessing: preprocess the collected power data; Feature extraction: extracting features related to the power operation status from the preprocessed data; Abnormal identification and detection: Based on the extracted features and using classification algorithms or machine learning algorithms, the operating status of the power device is identified, and the actual power data is compared with the corresponding normal range or threshold one by one to determine whether the power device has power abnormalities; Information extraction: Extract abnormal information of power devices based on the results of abnormal identification and detection; Result output: The extracted abnormal information is sent to the power data supervision module and early warning module via the cloud management platform.

9. The power-based MR virtual visualization space safety supervision system according to claim 1 is characterized in that: The cloud management platform is in communication connection with the supervision alarm generation module. The supervision alarm generation module is used to collect the time point when the power data supervision module receives the corresponding abnormal information and the time point when the supervision operation is started when the power data supervision module performs the corresponding supervision operation on the power device, and mark them as the information sending time point and the instruction feedback time point respectively, and calculate the time difference between the instruction feedback time point and the information sending time point to obtain the supervision effectiveness value; The timing starts from the time when the information is sent to obtain the supervision and adjustment duration; if the supervision and adjustment duration reaches the corresponding preset duration value threshold and the power data supervision module fails to successfully complete the regulation of the power device, a supervision abnormality alarm information is generated, and the supervision abnormality alarm information is sent to the early warning module via the cloud management platform. The early warning module displays the supervision abnormality alarm information and issues corresponding early warning information.

10. The power-based MR virtual visualization space safety supervision system according to claim 9, characterized in that: Set the supervision cycle, collect the number of supervision abnormality alarm information generated within the supervision cycle and mark it as the supervision abnormality frequency value GYP, and sum and calculate all the supervision effective values ​​within the supervision cycle and take the average to obtain the supervision risk value GF, and calculate the ratio of the supervision abnormality frequency value to the number of abnormal information received by the power data supervision module within the supervision cycle to obtain the supervision abnormality frequency ratio value GYZ. Obtain the regulatory warning value, where f1, f2, and f3 are preset proportional coefficients, and the values ​​of f1, f2, and f3 are all greater than zero, and compare and analyze the regulatory warning value GY with the preset regulatory warning value threshold value entered and stored internally; If the regulatory warning value GY is greater than the preset regulatory warning value threshold, a high-risk regulatory signal is generated and sent to the warning module via the cloud management platform. When the warning module receives the high-risk regulatory signal, it issues a corresponding warning message.

Images