Portable rapid temperature and pressure detection method and system

Abstract

The invention relates to the technical field of temperature and pressure monitoring, and discloses a portable rapid temperature and pressure detection method and system, and the method comprises the following steps: enabling a portable measurement meter to be in communication connection with a mobile terminal; collecting real-time temperature and pressure data of the to-be-detected pipeline; identification of detection error data is realized according to a comparison result of the real-time detection data and the range threshold value; correcting the detection error data, and replacing the detection error data in the real-time detection data with the corrected data; and transmitting the corrected real-time detection data to the mobile terminal, and displaying the positions, temperatures, pressures and measurement time data of all detection points in the to-be-detected pipeline. Through the combination of the portable detection equipment, the intelligent algorithm and the wireless communication technology, the portable, rapid and accurate real-time monitoring of the temperature and pressure of the pipeline system is realized, the system has the functions of automatic abnormity correction and remote monitoring, and the operation safety and efficiency of the pipeline system are effectively improved.

Description

Technical Field

[0001] The present invention relates to the technical field of temperature and pressure monitoring, and in particular to a portable rapid temperature and pressure detection method and system. Background Art

[0002] At present, in order to ensure the stability of the system and the heating (cooling) effect during the operation of the heating (cooling) system, the operators need to monitor the key parameters in the system in real time, such as water temperature, pressure and hydraulic balance. Monitoring of water temperature helps to confirm whether the terminal water supply temperature matches the output of the heat (cooling) source, so as to evaluate the smoothness of the circulation system and the status of the pipeline. If there is a large difference between the terminal water supply temperature and the temperature of the heat (cooling) source, this may indicate that there is a problem with the circulation system and adjustment or maintenance is required. Pressure monitoring in the system is equally important because the heating or cooling system usually operates under pressure. Stable pressure is the key to ensuring the safe operation of the system, and any abnormal fluctuations in pressure may indicate that there are leaks or other problems in the system. Leakages can cause energy loss and affect the quality of heating (cooling), so it is necessary to locate the leak by checking each area.

[0003] In addition, hydraulic balance is also an important aspect in the operation of the heating (cooling) system. The detection of hydraulic balance can be achieved by comparing the pressure difference between the supply and return water at each end. If the system is hydraulically balanced, the pressure difference at each end should be consistent. If the pressure difference at a certain end is too large or too small, this may indicate that the hydraulic state of the end is abnormal, and the flow needs to be adjusted to ensure the suitability of the room temperature. Another way to monitor hydraulic balance is to observe the return water temperature at each end. If the system is hydraulically balanced, the return water temperature at each end should be consistent. If the return water temperature at a certain point is abnormal, this may indicate that the branch flow at that end is abnormal and needs to be adjusted accordingly.

[0004] In summary, during the operation of the heating (cooling) system, real-time monitoring of the temperature, pressure and hydraulic balance in the pipeline network is the key to ensuring the stability of the system and the heating (cooling) effect. Therefore, how to achieve portable, real-time and accurate detection of the temperature and pressure in the pipeline, and automatically and efficiently correct the abnormalities when detection error data occurs, has become a technical problem that needs to be solved urgently. Summary of the invention

[0005] In view of the problems in the related art, the present invention proposes a portable rapid temperature and pressure detection method and system to overcome the above-mentioned technical problems existing in the existing related art.

[0006] To this end, the specific technical solution adopted by the present invention is as follows:

[0007] According to one aspect of the present invention, a portable rapid temperature and pressure detection method is provided, and the portable rapid temperature and pressure detection method comprises the following steps:

[0008] S1. Install a portable measuring meter on the pipeline according to the detection requirements, and connect the portable measuring meter to the mobile terminal for communication; select a detection point through the mobile terminal, start the portable measuring meter at the detection point, and collect real-time temperature and pressure data of the pipeline to be detected;

[0009] S2. Based on pipeline parameters, medium characteristics and environmental conditions, combined with the initial data of cold / heat sources, determine the temperature and pressure range thresholds in the pipeline to be detected, and identify the detection error data based on the comparison results of the real-time detection data and the range thresholds;

[0010] S3, based on the radial basis function neural network model, correcting the detection error data, and using the corrected data to replace the detection error data in the real-time detection data;

[0011] S4. Based on wireless communication technology, the corrected real-time detection data is transmitted to the mobile terminal, and the location, temperature, pressure and measurement time data of all detection points in the pipeline to be detected are displayed on the mobile terminal.

[0012] Preferably, the portable measuring meter is installed on the pipeline according to the detection requirements, and the portable measuring meter is connected to the mobile terminal for communication; the detection point is selected by the mobile terminal, the portable measuring meter at the detection point is started, and the real-time temperature and pressure data of the pipeline to be detected are collected, which includes the following steps:

[0013] S11, determine the area to be tested, and insert the portable measuring meter into the pipe clamp pre-installed on the pipeline through the measuring joint;

[0014] S12, establishing a communication connection between the portable measuring meter and the mobile terminal based on wireless communication technology, and selecting a detection point through the mobile terminal;

[0015] S13. According to the selected detection point, the portable measuring meter at the detection point is started to collect the real-time temperature and pressure data of the pipeline to be detected.

[0016] Preferably, the method of determining the temperature and pressure range thresholds in the pipeline to be detected based on pipeline parameters, medium characteristics and environmental conditions in combination with initial data of cold / heat sources, and identifying the detection error data according to the comparison result of the real-time detection data and the range thresholds includes the following steps:

[0017] S21, based on pipeline parameters, medium characteristics and environmental conditions, combined with initial data of the cold / heat source, determine the temperature range threshold and pressure range threshold of the cold / heat source in the pipeline to be detected;

[0018] S22, judging whether the real-time temperature and pressure meet the temperature range threshold and the pressure range threshold, if so, judging that the real-time detection data is normal, if not, judging that the real-time detection data is detection error data.

[0019] Preferably, the step of determining the temperature range threshold and pressure range threshold of the cold / heat source in the pipeline to be detected based on pipeline parameters, medium characteristics and environmental conditions in combination with initial data of the cold / heat source comprises the following steps:

[0020] S211, obtaining pipeline parameters, medium parameters and real-time ambient temperature, and collecting the initial temperature, initial pressure, preset flow rate and flow rate of the cold / heat source;

[0021] S212. Calculate the temperature of the cold / heat source medium at different positions in the pipeline based on the principles of heat conduction and convection heat transfer;

[0022] S213. Based on the principles of fluid dynamics, calculate the pressure of the cold / heat source medium at different positions in the pipeline;

[0023] S214. Determine the temperature range threshold and pressure range threshold of the cold / heat source during operation according to the calculation result and the preset allowable fluctuation range.

[0024] Preferably, the temperature of the medium in the pipeline is calculated as follows:

[0025]

[0026] In the formula, T(x) represents the temperature of the medium at a distance x; T0 represents the initial temperature of the medium; T' represents the ambient temperature; h represents the heat transfer coefficient of the pipeline; A represents the inner circumference of the pipeline; Indicates mass flow rate; C p represents the specific heat capacity of the medium; x represents the length position of the pipeline; ρ represents the density of the medium; v represents the flow velocity of the medium.

[0027] Preferably, the calculation formula for the pressure of the medium in the pipeline is:

[0028]

[0029] In the formula, P(x) represents the pressure of the medium at a distance x; P0 represents the initial pressure at the inlet of the pipeline; f represents the friction factor of the pipeline; x represents the longitudinal position of the pipeline; D represents the diameter of the pipeline; ρ represents the density of the medium; v represents the flow velocity of the medium; g represents the acceleration of gravity; z0 represents the height at the inlet of the pipeline; z x Represents the height at distance x in the pipe.

[0030] Preferably, the method of correcting the detection error data based on the radial basis function neural network model and replacing the detection error data in the real-time detection data with the corrected data includes the following steps:

[0031] S31, obtaining the detection error data obtained through identification, and clustering the detection error data using an ant colony optimization algorithm;

[0032] S32, constructing a radial basis function neural network model, and adjusting the center and width of the radial basis function using an ant colony optimization algorithm to obtain an optimized radial basis function neural network model;

[0033] S33, inputting the clustered detection error data into the optimized radial basis function neural network model to obtain corrected data;

[0034] S34, ensuring that the corrected data meets a preset threshold range, and using the corrected data that meets the preset threshold range to replace the detection error data in the original detection data.

[0035] Preferably, the step of acquiring the identified detection error data and clustering the detection error data using an ant colony optimization algorithm comprises the following steps:

[0036] S311, obtaining the detection error data obtained through identification, setting the number of ant individuals according to the number of detection error data points, and each ant represents one detection error data point;

[0037] S312, setting the number of ants, pheromone concentration, evaporation coefficient and maximum number of iterations, and assigning an initial pheromone concentration to the path of each detection error data point;

[0038] S313, using the Euclidean distance to calculate the similarity of the detection error data points, and guiding the ants to move according to the similarity between the detection error data points and the pheromone concentration on the path, so as to gradually form clusters;

[0039] S314, dynamically update the pheromone on the path to guide the ants to form the optimal clustering; determine whether the clustering result tends to be stable or reaches the maximum number of iterations, if not, continue to execute the iteration, if so, output the clustering affiliation of each detection error data point.

[0040] Preferably, the step of constructing a radial basis function neural network model and adjusting the center and width of the radial basis function using an ant colony optimization algorithm to obtain an optimized radial basis function neural network model comprises the following steps:

[0041] S321, constructing a basic radial basis function neural network, setting an initial center and width, and training the radial basis function neural network;

[0042] S322, initializing the number of ants, pheromone concentration, and initial values ​​of the center and width of the radial basis function; defining an objective function to minimize the prediction error of the radial basis function neural network;

[0043] S323, calculating the path selection probability of each ant according to the center and width of the radial basis function; guiding the ant to move according to the selection probability, and adjusting the corresponding radial basis function center and width;

[0044] S324, updating the pheromone concentration on the path selected by the ant according to the optimization effect of the objective function; performing multiple iterations, and gradually finding the optimal radial basis function center and width by adjusting the path each time;

[0045] S325. Determine whether the maximum number of iterations has been reached or the objective function has converged to a specified threshold. If not, continue to iterate. If so, output the center and width of the optimal radial basis function to obtain an optimized radial basis function neural network model.

[0046] According to another aspect of the present invention, there is provided a portable rapid temperature and pressure detection system, the portable rapid temperature and pressure detection system comprising a data acquisition module, an error identification module, an error correction module and a temperature and pressure data display module;

[0047] The data acquisition module is used to install a portable measuring meter on the pipeline according to the detection requirements, and connect the portable measuring meter to the mobile terminal for communication; select the detection point through the mobile terminal, start the portable measuring meter at the detection point, and collect the real-time temperature and pressure data of the pipeline to be detected;

[0048] The error identification module is used to determine the temperature and pressure range thresholds in the pipeline to be detected based on pipeline parameters, medium characteristics and environmental conditions, combined with the initial data of the cold / heat source, and to identify the detection error data based on the comparison results of the real-time detection data and the range thresholds;

[0049] The error correction module is used to correct the detection error data based on the radial basis function neural network model, and replace the detection error data in the real-time detection data with the corrected data;

[0050] The temperature and pressure data display module is used to transmit the corrected real-time detection data to the mobile terminal based on wireless communication technology, and display the position, temperature, pressure and measurement time data of all detection points in the pipeline to be detected through the mobile terminal.

[0051] Compared with the prior art, the present invention provides a portable rapid temperature and pressure detection method and system, which has the following beneficial effects:

[0052] (1) The present invention realizes portable, rapid, and accurate real-time monitoring of the temperature and pressure of the pipeline system through the combination of portable detection equipment, intelligent algorithms, and wireless communication technology. It also has the functions of automatic abnormal correction and remote monitoring, effectively improving the operational safety and efficiency of the pipeline system.

[0053] (2) The present invention installs a portable measuring meter on the pipeline and connects it to the mobile terminal for communication. The user can flexibly select the detection point through the mobile device and collect the temperature and pressure data of the pipeline to be detected in real time, thereby not only simplifying the equipment installation but also having efficient data collection capabilities, which is particularly suitable for complex or space-constrained pipeline systems.

[0054] (3) The present invention can dynamically calculate and set the reasonable range threshold of temperature and pressure in the pipeline by combining pipeline parameters, medium characteristics, initial data of cold / heat sources and environmental conditions, and compare the collected data with the threshold range in real time to timely identify the detection error data. At the same time, based on the radial basis function neural network model, the detected detection error data can be automatically corrected to eliminate the influence caused by environmental or sensor errors, ensuring the accuracy and reliability of the data.

[0055] (4) The present invention clusters the detection error data through the ant colony optimization algorithm, classifies similar detection error data, and helps to further analyze the abnormal patterns of the data. At the same time, the parameters of the radial basis function neural network model are adjusted by ant colony optimization, the correction accuracy of the model is optimized, and the accuracy and efficiency of the correction of the detection error data are improved. Whether it is the temperature or pressure detection error data, after the model correction, it can meet the preset threshold range, and the system can autonomously replace the original detection error data, ensuring the safe operation of the entire pipeline system.

[0056] (5) The corrected detection data of the present invention is transmitted to the mobile terminal through wireless communication technology, and the user can view the location, temperature, pressure, measurement time and other information of each detection point in real time, thereby not only improving the monitoring efficiency of the pipeline system and reducing manual intervention, but also making remote monitoring and management more convenient. BRIEF DESCRIPTION OF THE DRAWINGS

[0057] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0058] Figure 1 It is a flow chart of a portable rapid temperature and pressure detection method according to an embodiment of the present invention. DETAILED DESCRIPTION

[0059] The following will be combined with 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 of 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.

[0060] According to an embodiment of the present invention, a portable rapid temperature and pressure detection method and system are provided.

[0061] The present invention is further described with reference to the accompanying drawings and specific embodiments. Figure 1 As shown, according to one embodiment of the present invention, a portable rapid temperature and pressure detection method is provided, and the portable rapid temperature and pressure detection method comprises the following steps:

[0062] S1. Install a portable measuring meter on the pipeline according to the detection requirements, and connect the portable measuring meter to the mobile terminal for communication; select a detection point through the mobile terminal, start the portable measuring meter at the detection point, and collect real-time temperature and pressure data of the pipeline to be detected;

[0063] The method of installing a portable measuring meter on the pipeline according to the detection requirements and connecting the portable measuring meter to the mobile terminal for communication; selecting a detection point through the mobile terminal, starting the portable measuring meter at the detection point, and collecting real-time temperature and pressure data of the pipeline to be detected includes the following steps:

[0064] S11, determine the area to be tested, and insert the portable measuring meter into the pipe clamp pre-installed on the pipeline through the measuring joint;

[0065] Specifically, the bottom of the pipe clamp is welded to the pipeline, and the other end is a quick connection interface; one end of the measuring joint is a quick-connect joint, and the other end is a quarter-point external thread, which is fixed to the pipe clamp thread; the portable measuring meter includes an instrument display screen, a transmitter and a metal probe, and the probe contains a piezoresistor and a platinum resistor.

[0066] S12, establishing a communication connection between the portable measuring meter and the mobile terminal based on wireless communication technology, and selecting a detection point through the mobile terminal;

[0067] S13. According to the selected detection point, the portable measuring meter at the detection point is started to collect the real-time temperature and pressure data of the pipeline to be detected.

[0068] Specifically, the mobile terminal has a built-in program that can pre-enter the heating (cooling) network diagram, which marks the location of each measuring point, and each measuring point corresponds to a QR code at a specific location. The operator can scan the QR code to understand the location information of the measuring point. After the probe is inserted into the measuring connector, the transmitter converts the resistance signals of temperature and pressure into analog signals. The temperature and pressure values ​​are updated every second, and there will be numerical fluctuations. The measurement table smoothes the measured values ​​and takes the average value of the latest 10 seconds for display. When the smoothed value no longer changes, the measurement is completed.

[0069] S2. Based on pipeline parameters, medium characteristics and environmental conditions, combined with the initial data of cold / heat sources, determine the temperature and pressure range thresholds in the pipeline to be detected, and identify the detection error data based on the comparison results of the real-time detection data and the range thresholds;

[0070] The method of determining the temperature and pressure range thresholds in the pipeline to be detected based on pipeline parameters, medium characteristics and environmental conditions in combination with the initial data of the cold / heat source, and identifying the detection error data according to the comparison result between the real-time detection data and the range thresholds includes the following steps:

[0071] S21, based on pipeline parameters, medium characteristics and environmental conditions, combined with initial data of the cold / heat source, determine the temperature range threshold and pressure range threshold of the cold / heat source in the pipeline to be detected;

[0072] Specifically, the method of determining the temperature range threshold and pressure range threshold of the cold / heat source in the pipeline to be detected based on the pipeline parameters, medium characteristics and environmental conditions and in combination with the initial data of the cold / heat source includes the following steps:

[0073] S211, obtaining pipeline parameters, medium parameters and real-time ambient temperature, and collecting the initial temperature, initial pressure, preset flow rate and flow rate of the cold / heat source;

[0074] Specifically, pipeline parameters include thermal conductivity, pressure resistance, etc., which determine the heat transfer process and the pressure range that the pipeline can withstand, as well as the length, diameter and cross-sectional area of ​​the pipeline, which affect the heat transfer and pressure drop of the medium;

[0075] Medium parameters include heat capacity, viscosity, density, etc., which determine the thermodynamic behavior of the medium when it is transported in the pipeline;

[0076] Initial temperature of heat source or cold source: Get the temperature of the source, which can be the temperature of liquid, gas or other medium in the initial state;

[0077] Initial pressure of the heat or cold source: The pressure data at the source, which is usually related to the rated operating conditions of the equipment;

[0078] Flow Rate: The rate at which a medium flows through a pipe, usually powered by a pump or compressor.

[0079] Flow rate: the volume flow rate or mass flow rate of the medium through the pipeline, usually volume flow rate (m 3 / s) or mass flow rate (kg / s).

[0080] S212. Calculate the temperature of the cold / heat source medium at different positions in the pipeline based on the principles of heat conduction and convection heat transfer;

[0081] Among them, the calculation formula for the temperature of the medium in the pipeline is:

[0082]

[0083] In the formula, T(x) represents the temperature of the medium at a distance x; T0 represents the initial temperature of the medium; T' represents the ambient temperature; h represents the heat transfer coefficient of the pipeline; A represents the inner circumference of the pipeline; Indicates mass flow rate; C p represents the specific heat capacity of the medium; x represents the length position of the pipeline; ρ represents the density of the medium; v represents the flow velocity of the medium.

[0084] S213. Based on the principles of fluid dynamics, calculate the pressure of the cold / heat source medium at different positions in the pipeline;

[0085] Among them, the calculation formula for the pressure of the medium in the pipeline is:

[0086]

[0087] In the formula, P(x) represents the pressure of the medium at a distance of x; P0 represents the initial pressure at the inlet of the pipeline; f represents the friction factor of the pipeline; x represents the longitudinal position of the pipeline; D represents the diameter of the pipeline; ρ represents the density of the medium; v represents the flow velocity of the medium; g represents the acceleration of gravity; z0 represents the height at the inlet of the pipeline, that is, the height of the fluid in the pipeline at position x=0, which is usually used to calculate the influence of height difference. If the inlet of the pipeline is at a higher place, the pressure of the fluid will increase during the flow due to the decrease in height; conversely, if it flows to a higher place, the pressure will decrease; z x It represents the height at distance x in the pipe, that is, the height at any position x in the pipe. x The difference between z0 and z0 can determine the change in gravitational potential energy of the fluid at this position, thereby affecting the pressure.

[0088] S214. Determine the temperature range threshold and pressure range threshold of the cold / heat source during operation according to the calculation result and the preset allowable fluctuation range.

[0089] Specifically, the temperature range threshold and pressure range threshold of the cold / heat source during operation are determined according to the calculation results, including:

[0090] Determine the maximum temperature threshold: Based on the calculated temperature distribution at different locations, ensure that the temperature does not exceed the maximum allowable temperature of the pipeline and equipment.

[0091] Determine the minimum temperature threshold: Based on process requirements and system requirements, avoid equipment damage or energy waste caused by too low a temperature. Set according to the system's minimum temperature requirements.

[0092] Determine the maximum pressure threshold: Ensure that the calculated pressure does not exceed the maximum allowable pressure based on the pressure-bearing capacity of the pipeline and equipment.

[0093] Determine the minimum pressure threshold: Ensure the minimum pressure to ensure stable fluid flow and avoid fluid stagnation or system failure due to too low pressure.

[0094] Combined with the preset allowable fluctuation range: In order to cope with fluctuations and uncertainties in operation, preset fluctuation values ​​are introduced on the maximum and minimum values ​​of temperature and pressure. In this embodiment, the preset fluctuation values ​​are as follows: maximum temperature fluctuation 2-5%; minimum temperature fluctuation 5-8%; maximum pressure fluctuation 1-3%; minimum pressure fluctuation 5-8%.

[0095] S22, judging whether the real-time temperature and pressure meet the temperature range threshold and the pressure range threshold, if so, judging that the real-time detection data is normal, if not, judging that the real-time detection data is detection error data.

[0096] S3, based on the radial basis function neural network model, correcting the detection error data, and using the corrected data to replace the detection error data in the real-time detection data;

[0097] The method of correcting the detection error data based on the radial basis function neural network model and replacing the detection error data in the real-time detection data with the corrected data includes the following steps:

[0098] S31, obtaining the detection error data obtained through identification, and clustering the detection error data using an ant colony optimization algorithm;

[0099] Specifically, the obtaining of the identified detection error data and clustering the detection error data using an ant colony optimization algorithm comprises the following steps:

[0100] S311, obtaining the detection error data obtained through identification, setting the number of ant individuals according to the number of detection error data points, and each ant represents one detection error data point;

[0101] S312, setting the number of ants, pheromone concentration, evaporation coefficient and maximum number of iterations, and assigning an initial pheromone concentration to each path of the detection error data point (i.e., cluster selection), which is usually a small positive number, indicating that the ants' exploration of the path is random at the beginning;

[0102] S313, using the Euclidean distance to calculate the similarity of the detection error data points, and guiding the ants to move according to the similarity between the detection error data points and the pheromone concentration on the path, gradually forming clusters; specifically including:

[0103] Calculate the similarity of data points, the formula is:

[0104]

[0105] Where d(i,j) represents the similarity between the detection error data points i and j, T i , P i Represent the temperature and pressure of the ith data point, T j , P j denote the temperature and pressure of the jth data point respectively;

[0106] Ant path selection and clustering: Each ant is clustered according to the similarity d between data points. ij and the pheromone concentration τ on the path ij To select the target point to move;

[0107] Ant movement: Based on the calculated selection probability, ants select the most likely next data point and gradually form clusters.

[0108] The formula for selection probability is:

[0109]

[0110] In the formula, p ij represents the probability of selection, α and β control the importance of pheromone and similarity respectively, i.e., weight factors, and k represents the index of all possible next nodes (candidate paths) to which the ant can move when it is at node i, so k represents all the candidate nodes that can be selected;

[0111] S314, dynamically update the pheromone on the path to guide the ants to form the optimal cluster; determine whether the clustering result tends to be stable or reaches the maximum number of iterations, if not, continue to execute the iteration, if so, output the clustering affiliation of each detection error data point. Specifically including:

[0112] Update pheromone: Every time the ants complete a path selection, pheromones are added along the path they have walked. At the same time, the pheromones are locally evaporated to prevent the ants from converging to the local optimal solution at an early stage. The pheromone update formula is: τij =(1-ρ)·τ ij +Δτ ij , where ρ is the evaporation coefficient, which controls the volatilization rate of pheromones, and Δτ ij is the pheromone increment contributed by the number of ants passing through the path.

[0113] Pheromone enhancement: As the number of iterations increases, the pheromone concentration on the optimal path will gradually increase, thereby guiding more ants to choose better clustering.

[0114] Prevent over-clustering: By controlling the increment of pheromone, we can avoid over-convergence to small clusters. We set a maximum number of clusters to ensure the rationality of clustering.

[0115] Termination condition: The algorithm terminates according to one of the following conditions (reaching the preset maximum number of iterations or the changes in ant path selection tend to be stable and the clustering results no longer change significantly). The final clustering result is that each cluster represents a group of similar detection error data points.

[0116] Output clustering results: All detection error data points are assigned to different groups according to the clustering results. Each group of data points represents similar abnormal situations that occur under specific conditions. The final clustering result indicates the category to which the detection error data belongs.

[0117] S32, constructing a radial basis function neural network model, and adjusting the center and width of the radial basis function using an ant colony optimization algorithm to obtain an optimized radial basis function neural network model;

[0118] Specifically, the step of constructing a radial basis function neural network model and adjusting the center and width of the radial basis function using an ant colony optimization algorithm to obtain an optimized radial basis function neural network model includes the following steps:

[0119] S321, constructing a basic radial basis function neural network, setting an initial center and width, and training the radial basis function neural network; specifically including:

[0120] 1) Initialize the radial basis function neural network model (RBFNN):

[0121] 1.1 Input Layer

[0122] Input: The input data is the feature vector of the detection error data (such as temperature, pressure, etc.).

[0123] Operation: The input layer directly receives the features of the detection error data as the input of the RBFNN. Assuming the input dimension is n, the input layer has n nodes.

[0124] 1.2 Hidden Layer

[0125] Input: Center, width and input data of the radial basis function.

[0126] Operation: Use radial basis function as activation function. The commonly used radial basis function is Gaussian function, which is expressed as:

[0127]

[0128] Where x is the input data, c is the center of the radial basis function, and σ is the width of the radial basis function;

[0129] Hidden layer nodes: The hidden layer has m nodes, each node corresponds to a radial basis function. Initially, the center c and width σ are randomly initialized.

[0130] 1.3 Output Layer

[0131] Input: The radial basis function value output by the hidden layer.

[0132] Operation: The output layer converts the output of the hidden layer into a prediction result through weighted summation. The activation function of the output layer is usually a linear function, and the prediction result is the corrected temperature or pressure value.

[0133] 2) Training the initial RBFNN model

[0134] 2.1 Training set preparation

[0135] Input: The data set used for training, including the input of the detection error data and the target value (for example, the corrected normal temperature or pressure).

[0136] Operation: Use the detection error data to build a training set. The input data is the detection error data feature, and the output is the expected correction value.

[0137] 2.2 RBFNN Training

[0138] Input: initial center c and width σ, and training data.

[0139] Operation: Adjust the network weights through conventional training algorithms (such as gradient descent), calculate the output of each hidden layer node, and minimize the error between the predicted value and the target value.

[0140] Output: The initially trained RBFNN model, but the center and width are not optimized at this time, and there is still room for optimization.

[0141] S322, initializing the number of ants, pheromone concentration, and initial values ​​of the center and width of the radial basis function; defining an objective function (the objective function can be defined as the prediction error of the RBFNN, such as the mean square error), and minimizing the prediction error of the radial basis function neural network;

[0142] S323, calculating the path selection probability of each ant according to the center and width of the radial basis function; guiding the ant to move according to the selection probability, and adjusting the corresponding radial basis function center and width;

[0143] S324, updating the pheromone concentration on the path selected by the ant according to the optimization effect of the objective function; performing multiple iterations, and gradually finding the optimal radial basis function center and width by adjusting the path each time;

[0144] S325. Determine whether the maximum number of iterations has been reached or the objective function has converged to a specified threshold. If not, continue to iterate. If so, output the center and width of the optimal radial basis function to obtain an optimized radial basis function neural network model.

[0145] S33, inputting the clustered detection error data into the optimized radial basis function neural network model to obtain corrected data;

[0146] S34, ensuring that the corrected data meets a preset threshold range, and using the corrected data that meets the preset threshold range to replace the detection error data in the original detection data.

[0147] S4. Based on wireless communication technology, the corrected real-time detection data is transmitted to the mobile terminal, and the location, temperature, pressure and measurement time data of all detection points in the pipeline to be detected are displayed on the mobile terminal.

[0148] Specifically, after on-site measurement, the temperature and pressure data are transmitted to the mobile terminal via Bluetooth or WiFi, and the corresponding measuring point location is selected for storage, including temperature value, pressure value and measurement time, and the data is visualized.

[0149] According to another embodiment of the present invention, there is provided a portable rapid temperature and pressure detection system, the portable rapid temperature and pressure detection system comprising a data acquisition module, an error identification module, an error correction module and a temperature and pressure data display module;

[0150] The data acquisition module is used to install a portable measuring meter on the pipeline according to the detection requirements, and connect the portable measuring meter to the mobile terminal for communication; select the detection point through the mobile terminal, start the portable measuring meter at the detection point, and collect the real-time temperature and pressure data of the pipeline to be detected;

[0151] The error identification module is used to determine the temperature and pressure range thresholds in the pipeline to be detected based on pipeline parameters, medium characteristics and environmental conditions, combined with the initial data of the cold / heat source, and to identify the detection error data based on the comparison results of the real-time detection data and the range thresholds;

[0152] The error correction module is used to correct the detection error data based on the radial basis function neural network model, and replace the detection error data in the real-time detection data with the corrected data;

[0153] The temperature and pressure data display module is used to transmit the corrected real-time detection data to the mobile terminal based on wireless communication technology, and display the position, temperature, pressure and measurement time data of all detection points in the pipeline to be detected through the mobile terminal.

[0154] In summary, with the help of the above technical solutions of the present invention, the present invention realizes portable, fast, accurate real-time monitoring of the temperature and pressure of the pipeline system through the combination of portable detection equipment, intelligent algorithm and wireless communication technology, and has the functions of automatic correction of abnormalities and remote monitoring, which effectively improves the operation safety and efficiency of the pipeline system. In addition, by installing a portable measuring meter on the pipeline and communicating with the mobile terminal, the user can flexibly select the detection point through the mobile device to collect the temperature and pressure data of the pipeline to be detected in real time, thereby not only simplifying the equipment installation, but also having efficient data collection capabilities, which is particularly suitable for complex or space-constrained pipeline systems. In addition, by combining pipeline parameters, medium characteristics, initial data of cold / heat sources and environmental conditions, the present invention can dynamically calculate and set the reasonable range threshold of the temperature and pressure in the pipeline, and compare the collected data with the threshold range in real time, and timely identify the detection error data. At the same time, based on the radial basis function neural network model, the detected detection error data can be automatically corrected to eliminate the influence caused by the environment or sensor error, and ensure the accuracy and reliability of the data. In addition, the present invention clusters the detection error data through the ant colony optimization algorithm, classifies similar detection error data, and helps to further analyze the abnormal mode of the data. At the same time, the parameters of the radial basis function neural network model are adjusted by ant colony optimization, the correction accuracy of the model is optimized, and the accuracy and efficiency of the correction of the detection error data are improved. After the model correction, the detection error data of both temperature and pressure can meet the preset threshold range, and the system can autonomously replace the original detection error data, ensuring the safe operation of the entire pipeline system. In addition, the corrected detection data of the present invention is transmitted to the mobile terminal through wireless communication technology, and the user can view the location, temperature, pressure and measurement time of each detection point in real time, thereby not only improving the monitoring efficiency of the pipeline system and reducing manual intervention, but also making remote monitoring and management more convenient.

[0155] The technical features of the above-mentioned embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification. A person of ordinary skill in the art can understand that all or part of the steps in the above-mentioned embodiment method can be completed by instructing the relevant hardware through a program. The program can be stored in a computer-readable storage medium. When the program is executed, it includes the steps described in the above method, and the storage medium, such as ROM / RAM, a disk, an optical disk, etc.

[0156] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A portable rapid temperature and pressure detection method, characterized in that: The portable rapid temperature and pressure detection method comprises the following steps: S1. Install a portable measuring meter on the pipeline according to the detection requirements, and connect the portable measuring meter to the mobile terminal for communication; select a detection point through the mobile terminal, start the portable measuring meter at the detection point, and collect real-time temperature and pressure data of the pipeline to be detected; S2. Based on pipeline parameters, medium characteristics and environmental conditions, combined with the initial data of cold / heat sources, determine the temperature and pressure range thresholds in the pipeline to be detected, and identify the detection error data based on the comparison results of the real-time detection data and the range thresholds; S3, based on the radial basis function neural network model, correcting the detection error data, and using the corrected data to replace the detection error data in the real-time detection data; S4. Based on wireless communication technology, the corrected real-time detection data is transmitted to the mobile terminal, and the location, temperature, pressure and measurement time data of all detection points in the pipeline to be detected are displayed on the mobile terminal.

2. A portable rapid temperature and pressure detection method according to claim 1, characterized in that: The method of installing a portable measuring meter on the pipeline according to the detection requirements and connecting the portable measuring meter to the mobile terminal for communication; selecting a detection point through the mobile terminal, starting the portable measuring meter at the detection point, and collecting real-time temperature and pressure data of the pipeline to be detected includes the following steps: S11, determine the area to be tested, and insert the portable measuring meter into the pipe clamp pre-installed on the pipeline through the measuring joint; S12, establishing a communication connection between the portable measuring meter and the mobile terminal based on wireless communication technology, and selecting a detection point through the mobile terminal; S13. According to the selected detection point, the portable measuring meter at the detection point is started to collect the real-time temperature and pressure data of the pipeline to be detected.

3. A portable rapid temperature and pressure detection method according to claim 1, characterized in that: The method of determining the temperature and pressure range thresholds in the pipeline to be detected based on the pipeline parameters, medium characteristics and environmental conditions in combination with the initial data of the cold / heat source, and realizing the identification of the detection error data according to the comparison result of the real-time detection data and the range thresholds includes the following steps: S21, based on pipeline parameters, medium characteristics and environmental conditions, combined with initial data of the cold / heat source, determine the temperature range threshold and pressure range threshold of the cold / heat source in the pipeline to be detected; S22, judging whether the real-time temperature and pressure meet the temperature range threshold and the pressure range threshold, if so, judging that the real-time detection data is normal, if not, judging that the real-time detection data is detection error data.

4. A portable rapid temperature and pressure detection method according to claim 3, characterized in that: The method of determining the temperature range threshold and pressure range threshold of the cold / heat source in the pipeline to be detected based on the pipeline parameters, medium characteristics and environmental conditions and in combination with the initial data of the cold / heat source comprises the following steps: S211, obtaining pipeline parameters, medium parameters and real-time ambient temperature, and collecting the initial temperature, initial pressure, preset flow rate and flow rate of the cold / heat source; S212. Calculate the temperature of the cold / heat source medium at different positions in the pipeline based on the principles of heat conduction and convection heat transfer; S213. Based on the principles of fluid dynamics, calculate the pressure of the cold / heat source medium at different positions in the pipeline; S214. Determine the temperature range threshold and pressure range threshold of the cold / heat source during operation according to the calculation result and the preset allowable fluctuation range.

5. A portable rapid temperature and pressure detection method according to claim 4, characterized in that: The calculation formula for the temperature of the medium in the pipeline is: In the formula, T(x) represents the temperature of the medium at a distance x; T0 represents the initial temperature of the medium; T' represents the ambient temperature; h represents the heat transfer coefficient of the pipeline; A represents the inner circumference of the pipeline; Indicates mass flow rate; C p represents the specific heat capacity of the medium; x represents the length position of the pipeline; ρ represents the density of the medium; v represents the flow velocity of the medium.

6. A portable rapid temperature and pressure detection method according to claim 4, characterized in that: The calculation formula for the medium pressure in the pipeline is: In the formula, P(x) represents the pressure of the medium at a distance x; P0 represents the initial pressure at the inlet of the pipeline; f represents the friction factor of the pipeline; x represents the longitudinal position of the pipeline; D represents the diameter of the pipeline; ρ represents the density of the medium; v represents the flow velocity of the medium; g represents the acceleration of gravity; z0 represents the height at the inlet of the pipeline; z x Represents the height at distance x in the pipe.

7. A portable rapid temperature and pressure detection method according to claim 1, characterized in that: The method of correcting the detection error data based on the radial basis function neural network model and replacing the detection error data in the real-time detection data with the corrected data includes the following steps: S31, obtaining the detection error data obtained through identification, and clustering the detection error data using an ant colony optimization algorithm; S32, constructing a radial basis function neural network model, and adjusting the center and width of the radial basis function using an ant colony optimization algorithm to obtain an optimized radial basis function neural network model; S33, inputting the clustered detection error data into the optimized radial basis function neural network model to obtain corrected data; S34, ensuring that the corrected data meets a preset threshold range, and using the corrected data that meets the preset threshold range to replace the detection error data in the original detection data.

8. A portable rapid temperature and pressure detection method according to claim 7, characterized in that: The step of obtaining the identified detection error data and clustering the detection error data using an ant colony optimization algorithm comprises the following steps: S311, obtaining the detection error data obtained through identification, setting the number of ant individuals according to the number of detection error data points, and each ant represents one detection error data point; S312, setting the number of ants, pheromone concentration, evaporation coefficient and maximum number of iterations, and assigning an initial pheromone concentration to the path of each detection error data point; S313, using the Euclidean distance to calculate the similarity of the detection error data points, and guiding the ants to move according to the similarity between the detection error data points and the pheromone concentration on the path, so as to gradually form clusters; S314, dynamically update the pheromone on the path to guide the ants to form the optimal clustering; determine whether the clustering result tends to be stable or reaches the maximum number of iterations, if not, continue to execute the iteration, if so, output the clustering affiliation of each detection error data point.

9. A portable rapid temperature and pressure detection method according to claim 7, characterized in that: The step of constructing a radial basis function neural network model and adjusting the center and width of the radial basis function using an ant colony optimization algorithm to obtain an optimized radial basis function neural network model comprises the following steps: S321, constructing a basic radial basis function neural network, setting an initial center and width, and training the radial basis function neural network; S322, initializing the number of ants, pheromone concentration, and initial values ​​of the center and width of the radial basis function; defining an objective function to minimize the prediction error of the radial basis function neural network; S323, calculating the path selection probability of each ant according to the center and width of the radial basis function; guiding the ant to move according to the selection probability, and adjusting the corresponding radial basis function center and width; S324, updating the pheromone concentration on the path selected by the ant according to the optimization effect of the objective function; performing multiple iterations, and gradually finding the optimal radial basis function center and width by adjusting the path each time; S325. Determine whether the maximum number of iterations has been reached or the objective function has converged to a specified threshold. If not, continue to iterate. If so, output the center and width of the optimal radial basis function to obtain an optimized radial basis function neural network model.

10. A portable rapid temperature and pressure detection system, used to implement the steps of the portable rapid temperature and pressure detection method according to any one of claims 1 to 9, characterized in that: The portable rapid temperature and pressure detection system includes a data acquisition module, an error identification module, an error correction module and a temperature and pressure data display module; The data acquisition module is used to install a portable measuring meter on the pipeline according to the detection requirements, and connect the portable measuring meter to the mobile terminal for communication; select the detection point through the mobile terminal, start the portable measuring meter at the detection point, and collect the real-time temperature and pressure data of the pipeline to be detected; The error identification module is used to determine the temperature and pressure range thresholds in the pipeline to be detected based on pipeline parameters, medium characteristics and environmental conditions, combined with the initial data of the cold / heat source, and to identify the detection error data based on the comparison results of the real-time detection data and the range thresholds; The error correction module is used to correct the detection error data based on the radial basis function neural network model, and replace the detection error data in the real-time detection data with the corrected data; The temperature and pressure data display module is used to transmit the corrected real-time detection data to the mobile terminal based on wireless communication technology, and display the position, temperature, pressure and measurement time data of all detection points in the pipeline to be detected through the mobile terminal.

Images