Urban underground pipe gallery transformer temperature intelligent inspection method and system

Abstract

The invention relates to the technical field of pipe gallery safety management, in particular to an urban underground pipe gallery transformer temperature intelligent inspection method and system, and the method comprises the following steps: collecting initial data through a collector of an information collection module; the microcomputer analyzes the environmental parameter data to form a fitting correction function, corrects the initial data according to the fitting correction function, and uploads the corrected initial data to the cloud information platform through the network transmitter; the cloud information platform receives the information uploaded by the network transmitter, stores the information and sends the information to the comprehensive early warning center; whether abnormal data exist in the data sent by the cloud information platform is judged through an upper computer of the comprehensive early warning center, if not, the data sent by the cloud information platform is displayed, and if yes, an alarm is given while the data sent by the cloud information platform is displayed. The technical problem that in the prior art, the time of a pipe gallery inspection method is too long, and sudden problems cannot be solved in time is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of utility tunnel safety management, and particularly relates to an intelligent inspection method and system for the temperature of transformers in urban underground utility tunnels. Background Art

[0002] With the development and utilization of urban underground space, the application of underground utility tunnels is becoming more and more extensive. As the urban underground lifeline, the underground utility tunnel concentrates the transportation of various urban core resources such as electricity, water, and heating. Among them, after the installation of power equipment in the underground utility tunnel, the problem of later maintenance often needs to be considered.

[0003] Currently, for the maintenance inspection of large transformers in urban underground utility tunnels, relevant departments often adopt the method of sending workers to conduct on-site inspections one by one. However, each underground utility tunnel often runs through the city, resulting in a too large distance between adjacent transformers, a long inspection process, and the inability to solve sudden problems in a timely manner. Summary of the Invention

[0004] The purpose of the present invention is to provide an intelligent inspection method and system for the temperature of transformers in urban underground utility tunnels, so as to solve the technical problem that the existing utility tunnel inspection method takes too long to solve sudden problems in a timely manner. The specific technical solutions are as follows:

[0005] The present invention provides a method for an intelligent inspection system for the temperature of transformers in urban underground utility tunnels, including the following steps:

[0006] S1. Collect initial data through the collector of the information collection module;

[0007] S2. Analyze the environmental parameter data through the microcomputer to form a fitting correction function, correct the initial data with reference to the fitting correction function, and upload it to the cloud information platform through the network transmitter;

[0008] S3. Receive the information uploaded by the network transmitter through the cloud information platform, store the information, and send it to the comprehensive early warning center;

[0009] S4. Judge whether there is abnormal data in the data sent by the cloud information platform through the upper computer of the comprehensive early warning center. If not, display the data sent by the cloud information platform. If so, display the data sent by the cloud information platform and give an alarm at the same time.

[0010] A further improvement of the intelligent inspection method for the temperature of transformers in urban underground utility tunnels of the present invention is that when analyzing the environmental parameter data through the microcomputer to form a fitting correction function, it specifically includes the following steps:

[0011] The density function of the influence of underground temperature on detection conforms to a normal distribution throughout the year, which can be expressed as:

[0012]

[0013] Among them, σ is the population standard deviation, μ is the population mean of the normal distribution, H(x) is a constant representing the upward offset of the normal distribution function at the current position, f(x) is the correction amount affected by the temperature of the underground utility tunnel, e is the natural constant, and x is the abscissa normalized by time to the annual scale;

[0014] The f(x) obtained after fitting represents the influence of the local underground temperature on the temperature measurement of the temperature sensor, and is used to correct the temperature monitoring result.

[0015] A further improvement of the intelligent temperature inspection method for transformers in the urban underground utility tunnel of the present invention lies in fitting according to the local monthly average temperature. The fitting method is to use an improved particle swarm optimization algorithm, and the objective function is set as:

[0016]

[0017] where i j is the average temperature of the current month, μ is the population mean of the normal distribution, σ is the population standard deviation, H(x) is a constant representing the upward offset of the normal distribution function of the current particle; F is the optimization objective function, n is the total number of the initial population, and j is the current particle;

[0018] Multiple individuals are generated using the random method. Each individual contains three data of σ, μ, and H(x), and the three data form a three-dimensional array. The population is put into the particle swarm optimization algorithm for iteration to solve the optimal solution when F is the smallest, that is, the optimal values of σ, μ, and H(x).

[0019] A further improvement of the intelligent temperature inspection method for transformers in the urban underground utility tunnel of the present invention lies in that the particle swarm optimization algorithm updates its own position by following the individual optimal value P best found by itself and the population optimal value G best found by the entire particle swarm. The velocity and position update formulas between the particle individual and the group are as follows:

[0020]

[0021] After calculating the objective function value of each particle each time, update its own position according to the above two formulas, that is, update the values of σ, μ, and H(x);

[0022] where is the running speed of the jth particle; n is the current iteration number; w j is the velocity inertia weight; is the running speed before the position and velocity update, c1 is the individual learning factor; c2 is the social learning factor; r1, r2 are probability random distribution numbers in the interval [0, 1], used to distribute the particle positions; is the current best position of the particle individual; is the current best position of the particle swarm, is the current position of the particle, is the position of the particle before the position and velocity are updated.

[0023] A further improvement of the intelligent inspection method for the temperature of transformers in urban underground pipe corridors according to the present invention lies in that, in the particle swarm algorithm, the inertial weight w j decreases linearly with the increase of the number of evolutionary iterations, and w j has the following relationship with the number of iterations:

[0024]

[0025] where gen max is the maximum number of iterations of the particle swarm, gen is the current number of iterations, and w max is the initially set maximum inertia coefficient, and w min is the initially set minimum inertia coefficient;

[0026] After the iteration is completed, the optimal fitting values of σ, μ, and H(x) are obtained, that is, the function expression that best conforms to the influence of the local underground temperature on temperature monitoring is obtained:

[0027]

[0028] A further improvement of the intelligent inspection method for the temperature of transformers in urban underground pipe corridors according to the present invention lies in that when correcting the initial data with reference to the fitting correction function, the measured data is adjusted according to the following fitting correction function;

[0029] T(x) = T n -ΔT = T n -f(x);

[0030] where T(x) is the actual temperature after correction, T n is the measured temperature, ΔT is the temperature correction amount, which is calculated by f(x).

[0031] By calculating through the T(x) formula, the influence of environmental factors on transformer temperature detection is excluded, and the most accurate transformer temperature is obtained, and then this temperature is sent to the cloud information platform.

[0032] The present invention also provides an intelligent inspection system for the temperature of transformers in urban underground pipe corridors, including:

[0033] An information collection module, the information collection module includes a collector, and the collector is used to install on the transformer to collect initial data;

[0034] An information distribution module, which includes a microcomputer and a network transmitter. The microcomputer analyzes the environmental parameter data to form a fitting correction function, corrects the initial data with reference to the fitting correction function, and uploads it to the cloud information platform through the network transmitter;

[0035] A cloud information platform, which is used to receive the information uploaded by the network transmitter, store the information, and then send it to the comprehensive early warning center;

[0036] A comprehensive early warning center, which includes a host computer. The host computer is used to display the data sent by the cloud information platform and alarm for abnormal data.

[0037] Applying the technical solution of the present invention has the following beneficial effects:

[0038] The intelligent temperature inspection system for transformers in urban underground pipe corridors of the present invention forms a fitting correction function by analyzing the environmental parameter data through the information distribution module, corrects the initial data with reference to the fitting correction function, thereby eliminating the influence of environmental factors on the transformer temperature detection, obtaining the most accurate transformer temperature, and sending it to the cloud information platform through the network transmitter. After receiving the data, the cloud information platform stores the data and sends it to the comprehensive early warning center. The comprehensive early warning center can view the transformer status information in real time and can retrieve the historical data stored in the cloud information platform through the network. When the transformer information is abnormal, the comprehensive early warning center will pop up an alarm so that the operator can eliminate the fault in time. After the abnormality is eliminated, the comprehensive early warning center records the fault information and continues to monitor the data, solving the technical problem in the prior art that the time for inspecting the pipe corridor is too long to solve sudden problems in time.

[0039] In addition to the purposes, features and advantages described above, the present invention has other purposes, features and advantages. The present invention will be further described in detail below with reference to the drawings. Description of the Drawings

[0040] The drawings forming a part of this application are used to provide a further understanding of the present invention. The schematic embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0041] Figure 1 is a schematic structural diagram of the intelligent temperature inspection system for transformers in urban underground pipe corridors of the present invention;

[0042] Figure 2 is a local underground monthly temperature coordinate chart;

[0043] Figure 3 is a particle swarm optimization algorithm flowchart of the intelligent temperature inspection method for transformers in urban underground pipe corridors of the present invention;

[0044] Figure 4 It is a schematic diagram of the installation position of the collector of the intelligent inspection system for the temperature of transformers in urban underground pipe corridors of the present invention.

[0045] Among them, 1. Information acquisition module; 2. Information distribution module; 3. Cloud information platform; 4. Comprehensive early warning center; 5. Microcomputer; 6. Network transmitter; 7. Transformer; 8. First temperature sensor; 9. Second temperature sensor; 10. Third temperature sensor. Specific implementation manner

[0046] The following will describe the embodiments of the present invention in detail with reference to the accompanying drawings.

[0047] See Figures 1 to 4 As shown, the present invention provides a method for an intelligent inspection system for the temperature of transformers in urban underground pipe corridors, including the following steps:

[0048] S1. Collect initial data through the collector of the information acquisition module;

[0049] S2. Analyze the environmental parameter data through the microcomputer to form a fitting correction function, correct the initial data with reference to the fitting correction function, and upload it to the cloud information platform through the network transmitter;

[0050] S3. Receive the information uploaded by the network transmitter through the cloud information platform, store the information, and send it to the comprehensive early warning center;

[0051] S4. The upper computer of the comprehensive early warning center judges whether there is abnormal data in the data sent by the cloud information platform. If not, display the data sent by the cloud information platform. If so, display the data sent by the cloud information platform and give an alarm at the same time.

[0052] Specifically, as Figure 2 shown, since the transformer underground pipe corridor is in the underground environment for a long time, the indoor temperature is greatly affected by seasonal changes, which may lead to problems such as temperature detection failure. Therefore, it is necessary to design a fitting correction function to correct the initial data. When forming a fitting correction function by analyzing the environmental parameter data through the microcomputer, it specifically includes the following steps:

[0053] The density function of the influence of underground temperature on detection conforms to the normal distribution throughout the year, which can be expressed as:

[0054]

[0055] Among them, σ is the population standard deviation, μ is the mean of the normal distribution population, H(x) is a constant representing the upward offset of the normal distribution function at the current position, f(x) is the correction amount affected by the temperature of the underground utility tunnel, e is the natural constant, and x is the abscissa after normalizing time to the annual scale;

[0056] The f(x) obtained after fitting represents the influence of the local underground temperature on the temperature measurement of the temperature sensor, and is used to correct the temperature monitoring result.

[0057] Preferably, as Figure 3 shown, fitting is performed according to the local monthly average temperature, and the fitting method is to use the improved particle swarm optimization algorithm, and the objective function is set as:

[0058]

[0059] where i j is the average temperature of the current month, μ is the mean of the normal distribution population, σ is the population standard deviation, H(x) is a constant representing the upward offset of the normal distribution function of the current particle; F is the optimization objective function, n is the total number of the initial population, and j is the current particle;

[0060] Multiple individuals are generated using the random method, and each individual contains three data of σ, μ, and H(x). The three data form a three-dimensional array. The population is put into the particle swarm optimization algorithm for iteration to solve the optimal solution when F is the smallest, that is, the optimal values of σ, μ, and H(x).

[0061] Preferably, the particle swarm optimization algorithm updates its own position by following the individual optimal value P best found by itself and the population optimal value G best found by the entire particle swarm. The velocity and position update formulas between the particle individual and the group are as follows:

[0062]

[0063] After calculating the objective function value of each particle each time, update its own position according to the above two formulas, that is, update the values of σ, μ, and H(x);

[0064] Among them, is the running speed of the j-th particle; n is the current iteration number; w j is the velocity inertia weight; is the running speed before position and velocity update, c1 is the individual learning factor; c2 is the social learning factor; r1, r2 are probability random distribution numbers in the interval [0, 1], used to distribute the particle position; is the current best position of the particle individual; is the current best position of the particle swarm, is the current position of the particle, is the particle position before position and speed update.

[0065] Preferably, in the particle swarm optimization algorithm, the inertia weight w j decreases linearly with the increase of the number of evolutionary iterations. The relationship between w j and the number of iterations is as follows:

[0066]

[0067] where gen max is the maximum number of iterations of the particle swarm, gen is the current number of iterations, and w max is the maximum inertia coefficient set initially, and w min is the minimum inertia coefficient set initially;

[0068] After the iteration is completed, the optimal fitting values of σ, μ, and H(x) are obtained, that is, the function expression that best conforms to the influence of the local underground temperature on temperature monitoring is obtained:

[0069]

[0070] Preferably, when correcting the initial data with reference to the fitting correction function, the measured data is adjusted according to the following fitting correction function;

[0071] T(x) = T n -ΔT = T n -f(x);

[0072] where T(x) is the actual temperature after correction, T n is the measured temperature, ΔT is the temperature correction amount, and is calculated by f(x).

[0073] By calculating with the T(x) formula, the influence of environmental factors on transformer temperature detection is excluded, and the most accurate transformer temperature is obtained, and then this temperature is sent to the cloud information platform.

[0074] Figure 3 The flowchart of the particle swarm optimization algorithm is shown in . The content of the flowchart is as follows: First, initialize the random particle positions and speeds, calculate the fitness of each particle, then update the particle's optimal position and the population's optimal position according to each fitness particle position and speed, perform iteration and judge whether the iteration ends. If so, end the entire calculation process. If not, update the position of the single particle according to the speed formula, and then judge whether there is a repeated optimal solution (i.e., local convergence). If not, return to calculate the fitness of each particle. If so, judge whether the iteration ends. If not, return to calculate the fitness of each particle. If so, end the entire calculation process.

[0075] The present invention also provides an intelligent inspection system for the temperature of transformers in urban underground pipe corridors, including:

[0076] An information collection module, the information collection module includes a collector, and the collector is used to be installed on a transformer to collect initial data;

[0077] An information distribution module, the information distribution module includes a microcomputer and a network transmitter. After analyzing the environmental parameter data through the microcomputer, a fitting correction function is formed, and the initial data is corrected with reference to the fitting correction function, and then uploaded to the cloud information platform through the network transmitter;

[0078] A cloud information platform, the cloud information platform is used to receive the information uploaded by the network transmitter, store the information and then send it to the comprehensive warning center;

[0079] A comprehensive warning center, the comprehensive warning center includes a host computer, and the host computer is used to display the data sent by the cloud information platform and alarm for abnormal data.

[0080] Specifically, in this embodiment, the collector is a temperature sensor. At least three temperature sensors are installed on the outer periphery of each transformer according to the manual inspection standard, and at least one temperature sensor is installed on both sides and the top surface of the transformer. As Figure 4 shown, the first temperature sensor is installed at the top position of the transformer, and the second temperature sensor and the third temperature sensor are respectively installed at both sides of the transformer. The microcomputer can adopt the TAM28335 model. The information collection module also includes a wireless transmission module, and the wireless transmission module sends the data of the temperature sensor to the information distribution module. The information distribution module also includes a WiFi module, and the corrected data is sent to the network transmitter through the WiFi module, and then sent to the cloud information platform by the network transmitter. The comprehensive warning center displays the real-time information of the transformer to the operator, and gives an alarm prompt by popping up a warning window when a sudden problem occurs, prompting the operator to eliminate the fault.

[0081] By reasonably designing the position of the initial information collection module, the present invention realizes quasi-artificial monitoring of the situation of the transformers in the underground pipe gallery, thereby accurately monitoring the real-time condition of the transformers and reducing the manpower loss caused by manual inspection; multiple information processing and distribution modules are buried in the pipe gallery. After analyzing the environmental parameter data, a fitting correction function is formed, and the initial data is corrected with reference to the fitting correction function to eliminate the influence of the room temperature in the underground pipe gallery on the monitoring module, making the data measurement more accurate. Then the corrected temperature data is uploaded to the cloud information platform for storage. The cloud information platform sends the information to the comprehensive warning center and alarms when the status information of the transformer is abnormal, enabling the staff to arrive at the scene quickly to solve sudden problems, solving potential safety hazards, realizing intelligent self-inspection of the transformers, and reducing the human resource burden of the inspection of the urban underground pipe gallery.

[0082] The intelligent inspection system for the temperature of transformers in urban underground pipe corridors of the present invention analyzes the environmental parameter data through an information distribution module to form a fitting correction function, and corrects the initial data with reference to the fitting correction function, thereby eliminating the influence of environmental factors on the transformer temperature detection, obtaining the most accurate transformer temperature, and sending it to the cloud information platform through a network transmitter. After receiving the data, the cloud information platform stores the data and sends it to the comprehensive warning center. The comprehensive warning center can view the transformer status information in real time and can retrieve the historical data stored in the cloud information platform through the network. When the transformer information is abnormal, the comprehensive warning center will pop up an alarm so that the operator can eliminate the fault in time. After the abnormality is eliminated, the comprehensive warning center records the fault information and continues to monitor the data, solving the technical problem in the prior art that the time for inspecting the pipe corridor is too long to solve sudden problems in time.

[0083] The present invention is applied to the temperature monitoring of transformers in the underground pipe corridors of Changsha City and is used to monitor the operating status of transformers in complex environments. The system collects environmental data in real time through temperature and humidity sensors, generates a fitting correction function using the information distribution module, eliminates environmental interference, obtains accurate transformer temperature data, and sends it to the cloud information platform for storage through the network. The comprehensive warning center monitors the transformer status in real time and supports the retrieval of historical data. The main functions of the system include:

[0084] Data collection and correction: The sensors collect environmental data, and the information distribution module generates a fitting correction function to correct the transformer temperature data.

[0085] Data transmission and storage: The corrected data is sent to the cloud platform for storage through the network.

[0086] Real-time monitoring: The warning center displays the transformer status in real time, and the operator can view the historical data at any time.

[0087] Abnormality handling: In the experiment, after giving the abnormal information of the transformer temperature, the system realizes an alarm and uploads the alarm information to the cloud platform. After the system records that the fault is eliminated, the information continues to be monitored.

[0088] The above are only the preferred embodiments of the present invention and are not used to limit the present invention. For those skilled in the art, the present invention can have various changes and modifications. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for an intelligent inspection system of the temperature of transformers in an urban underground pipe gallery, characterized in that, It includes the following steps: S1. Collect initial data through the collector of the information collection module; S2. Analyze the environmental parameter data by the microcomputer to form a fitting correction function, correct the initial data with reference to the fitting correction function, and upload it to the cloud information platform through the network transmitter; S3. Receive the information uploaded by the network transmitter through the cloud information platform, store the information, and then send it to the comprehensive warning center; S4. Use the upper computer of the comprehensive warning center to judge whether there is abnormal data in the data sent by the cloud information platform. If not, display the data sent by the cloud information platform. If so, display the data sent by the cloud information platform and give an alarm at the same time.

2. The intelligent inspection method for transformer temperature in urban underground pipe corridors according to claim 1, characterized in that When analyzing the environmental parameter data by the microcomputer to form a fitting correction function, it specifically includes the following steps: The density function of the influence of underground temperature on detection conforms to the normal distribution throughout the year, which can be expressed as: Among them, σ is the overall standard deviation, μ is the overall mean of the normal distribution, H(x) is a constant representing the upward offset of the normal distribution function at the current position, f(x) is the correction amount after the influence of the temperature in the underground utility tunnel, e is the natural constant, and x is the abscissa after normalizing the time to the year; The f(x) obtained after fitting represents the influence of the local underground temperature on the temperature measurement of the temperature sensor, and is used to correct the temperature monitoring result.

3. The intelligent inspection method for the temperature of the transformer in the urban underground pipe gallery according to claim 2, wherein Fit according to the local monthly average temperature. The fitting method is to use the improved particle swarm algorithm, and set the objective function as: where i j is the average temperature of the current month, μ is the mean of the normal distribution population, σ is the population standard deviation, H(j) is a constant representing the upward offset of the normal distribution function of the current particle; F is the optimization objective function, n is the total number of the initial population, and j is the current particle; Generate multiple individuals using the random method. Each individual contains three data of σ, μ, and H(x). The three data form a three-dimensional array. Put this population into the particle swarm algorithm for iteration to solve the optimal solution when F is the smallest, that is, the optimal values of σ, μ, and H(x).

4. The intelligent inspection method for the temperature of the transformer in the urban underground pipe gallery according to claim 3, characterized in that, The particle swarm optimization algorithm updates its own position by following the individual optimal value P found by itself best and the global optimal value G found by the entire particle swarm best to update its own position. The velocity and position update formulas between the particle individuals and the group are as follows: After calculating the objective function value of each particle each time, update its own position according to the above two formulas, that is, update the values of σ, μ, and H(x); Among them, is the running speed of the j-th particle; n is the current iteration number; w j is the velocity inertia weight; is the running speed before position and velocity update, c1 is the individual learning factor; c2 is the social learning factor; r1, r2 are probability random distribution numbers on the interval [0, 1], used to distribute the particle positions; is the current best position of the particle individual; is the current best position of the particle swarm, is the current position of the particle, is the particle position before position and velocity update.

5. The intelligent inspection method for the temperature of the transformer in the urban underground pipe gallery according to claim 4, wherein, In the particle swarm optimization algorithm, the inertia weight w j decreases linearly with the increase of the number of evolutionary iterations. The relationship between w j and the number of iterations is as follows: Among them, gen max is the maximum number of iterations of the particle swarm, gen is the current number of iterations, w max is the initially set maximum inertia coefficient, w min is the initially set minimum inertia coefficient; After the iteration is completed, the optimal fitting values of σ, μ, and H(x) are obtained, that is, the function expression that best conforms to the influence of the local underground temperature on the temperature monitoring is obtained:

6. The intelligent inspection method for the temperature of the transformer in the urban underground pipe gallery according to claim 5, wherein When correcting the initial data with reference to the fitting correction function, adjust the measured data according to the following fitting correction function; T(x) = T n -ΔT = T n -f(x); Among them, T(x) is the actual temperature after correction, T n is the measured temperature, and ΔT is the temperature correction amount, which is calculated by f(x). Through the calculation of the T(x) formula, eliminate the influence of environmental factors on the transformer temperature detection, obtain the most accurate transformer temperature, and then send this temperature to the cloud information platform.

7. A system adopting the intelligent temperature inspection method for transformers in urban underground pipe corridors as shown in claim 1, characterized in that, It includes: An information collection module, which includes a collector. The collector is used to be installed on the transformer to collect initial data; An information distribution module, which includes a microcomputer and a network transmitter. Analyze the environmental parameter data by the microcomputer to form a fitting correction function, correct the initial data with reference to the fitting correction function, and upload it to the cloud information platform through the network transmitter; A cloud information platform, which is used to receive the information uploaded by the network transmitter, store the information, and then send it to the comprehensive warning center; A comprehensive warning center, which includes an upper computer. The upper computer is used to display the data sent by the cloud information platform and give an alarm for abnormal data.

Images