A method for predicting mass concrete strength based on LoRa
Through LoRa wireless communication and BP neural network, real-time monitoring and prediction of large-volume concrete strength is achieved, high cost and low efficiency problems in the existing technology are solved, and automated concrete strength monitoring and early warning functions are provided.
Patent Information
- Application Number
- CN202210921084.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2022-08-02
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing large-volume concrete condition monitoring system relies on field readings and manual evaluation, is expensive and cannot automatically obtain and transmit concrete strength data, and lacks real-time monitoring and prediction functions.
Using a LoRa-based system, the lower computer module collects concrete temperature and humidity data and transmits it to the upper computer module through the LoRa wireless serial port module. The concrete strength prediction model is established using the BP neural network to output the concrete strength prediction results in real time.
It realizes that the monitoring personnel can view the concrete temperature and humidity data in real time, automatically calculate the concrete strength, and issue warnings in a timely manner, reducing on-site operation costs and improving monitoring efficiency and accuracy.
Smart Images

Figure CN115308388B_ABST
Abstract
Description
Technical Field
[0001] The present application relates to a concrete strength prediction method, and in particular to a large-volume concrete strength prediction method based on LoRa, and belongs to the technical field of concrete strength prediction. Background Art
[0002] The curing of large-volume cap concrete is an important task to ensure the smooth solidification of concrete. At present, thermocouples and handheld instruments are mainly used on site to provide data for concrete curing, and the parameters are all recorded and calculated manually. It is impossible to automatically obtain, transmit and calculate the data, which consumes a lot of manpower. Most of the existing large-volume cap concrete status monitoring systems are based on RS485 wired communication systems. Monitoring personnel must go to the site to read and evaluate, which is costly and does not have the function of detecting the existing concrete strength. Summary of the invention
[0003] A brief overview of the present invention is provided below in order to provide a basic understanding of certain aspects of the present invention. It should be understood that this overview is not an exhaustive overview of the present invention. It is not intended to identify key or important parts of the present invention, nor is it intended to limit the scope of the present invention. Its purpose is merely to present certain concepts in a simplified form as a prelude to a more detailed description discussed later.
[0004] In view of this, in order to solve the technical problems in the prior art that monitoring personnel must go to the site to read and evaluate, which is costly and has no function of detecting the existing concrete strength, the present invention provides a large-volume concrete strength prediction method based on LoRa.
[0005] A method for predicting the strength of large-volume concrete based on LoRa, wherein the lower computer module collects concrete temperature and humidity data and transmits the collected data to the upper computer module, and the upper computer module establishes a concrete strength prediction model of a BP neural network according to the concrete temperature and humidity data and the concrete strength data and outputs the concrete strength prediction result;
[0006] The lower computer module includes: a main control chip, a temperature acquisition card, a temperature and humidity sensor, a LoRa wireless serial port module and a relay module;
[0007] The main control chip includes a temperature acquisition card, a temperature and humidity sensor, a LoRa wireless serial port module and a relay module;
[0008] The main control chip is powered by 12V DC, and the two serial ports are connected to the wireless transmission module and the temperature acquisition card respectively; the 32-way IO port is used to control the relay;
[0009] The temperature acquisition card is connected to the temperature and humidity sensor, powered by a 24V DC power supply, with 12 temperature and humidity sensor inputs, connected to the temperature measuring probe, set a sampling frequency of 1Hz, connected to the serial port of the main control chip through the RS485 bus and the SP3485 chip, and uses the MODBUSRTU communication protocol for data interaction;
[0010] The temperature and humidity sensor is used for temperature measurement. The probe is connected to a three-core shielded wire and powered by a 5V power supply output by a temperature acquisition card. The temperature measurement range is 55°C to +125°C, and the measurement error is 1°C.
[0011] The relay module is connected to the temperature acquisition card via the RS485 bus, with a total of 34 channels, 32 of which are used to control the power supply of the temperature probe, one for controlling the power supply of the acquisition card, and one for controlling the power supply of 32 relays, using the 5V voltage output by D-50B for power supply;
[0012] The LoRa wireless serial port module is used to establish two-way communication between the upper computer module and the lower computer module; the power of the LoRa wireless serial port module is 1W, LoRa spread spectrum modulation and many-to-one network, using the 433MHz frequency band, and the custom channel specifies the data transmission direction;
[0013] The upper computer module is used to receive and display the data transmitted by the lower computer and the concrete strength prediction result.
[0014] Preferably, the method for obtaining concrete strength data is: collect the surface temperature (℃) data at a certain moment, record the duration of the temperature at this moment (h), and find the equivalent coefficient α corresponding to the surface temperature at this moment through the temperature corresponding equivalent coefficient table T , the temperature duration and α at this moment T Substitute t = Σα T t T Calculate t and substitute t into D. The concrete strength f(N / mm 2 ).
[0015] Preferably, the lower computer module acquisition process includes the following steps:
[0016] S110. Arrange measurement points at one quarter of the base, and use 8 temperature and humidity sensors to measure the ambient temperature, maximum temperature, peak temperature, surface temperature, bottom temperature, water inlet temperature, water outlet temperature and center temperature respectively.
[0017] S120. Configuration module, the LoRa communication module uses the fixed-point transparent transmission function, configures the lower computer acquisition module and the corresponding upper computer module with the same module address, adjusts the airspeed to 0.3K, and configures the temperature acquisition card with a different module address;
[0018] S130. Configure the host computer module debugging interface, fill in the route and the base part, record the time point of cooling water injection into the mass concrete, input the mold temperature value, input parameter alarm threshold and input center temperature;
[0019] S140. Read the temperature data collected by the temperature acquisition card, turn on the power of the acquisition card and the temperature probe, use the RS485 bus to send a read command to the temperature acquisition card, send the device number, function number, register address, number of registers and calculate the CRC check code according to the MOBBUSRTU protocol, read the data returned by the temperature acquisition card after sending the command, use the CRC check to verify whether the correct data format is received, and extract the temperature of each sampling point in the received data;
[0020] S150. After receiving the data, determine whether the data acquisition card is working normally. When the temperature acquisition card cannot collect data, disconnect the power of all temperature probes and connect them one by one, disconnect the power of the damaged measuring point, connect the normal measuring point, and turn off the power of the peripheral after re-reading the normal data;
[0021] S160. Use the LoRa wireless serial port module to send the collected data to the host computer module;
[0022] Preferably, the host computer module acquisition process includes the following steps:
[0023] S220. Call VISA serial port resources to obtain a string containing data, format and scan the string, the first two letters represent the location of the temperature measuring point, obtain temperature information according to the location of the measuring point, remove the damaged measuring point according to the value after obtaining the temperature information, the value collected when the temperature probe fails to be powered is 85, and the value collected when the probe is damaged is 0, remove the above two values to obtain the correct value, and obtain the temperature of each measuring layer, the inlet and outlet water temperature, and the ambient temperature;
[0024] S230. Obtain all temperature data every ten minutes;
[0025] S240. All temperature measurement data of the top layer and the bottom layer are summed and averaged to obtain the top layer temperature and the bottom layer temperature, the maximum value of the middle layer temperature is taken as the highest temperature of the platform, and the change of the highest temperature is recorded. The maximum value of the highest temperature during the measurement process is the peak temperature. The center temperature is obtained from the middle layer data, and a center temperature change curve is drawn. The outlet water temperature is subtracted from the inlet water temperature to obtain the inlet and outlet water temperature difference, the maximum temperature is subtracted from the surface temperature to obtain the surface-inside temperature difference, and the surface temperature is subtracted from the ambient temperature to obtain the ring-surface temperature difference. The temperature is taken every four hours to calculate the center temperature change rate as the cooling rate;
[0026] S250. The top layer temperature, middle layer temperature and bottom layer temperature data are compared with the parameter alarm threshold. If the threshold is exceeded, an alarm is issued. If the threshold is not exceeded, the next step is executed.
[0027] S260. Input the temperature data of 8 sensor sites at a certain moment into the concrete flow rate prediction model of the BP neural network to output the concrete strength prediction result.
[0028] Preferably, the concrete strength prediction model of the BP neural network includes an input layer, a hidden layer 1, a hidden layer 2 and an output layer; t1...t n The temperature of 8 concrete points at multiple times and the calibrated strength of concrete are input to the input layer, and a nonlinear mapping relationship is constructed with the concrete strength data through the hidden layer, and the output layer outputs the concrete strength;
[0029] The concrete strength prediction model training process of the BP neural network is as follows:
[0030] The concrete strength prediction model consists of three parts: training set, test set, and validation set. The prediction process is divided into the following three steps:
[0031] Step 1: The training set includes concrete temperature and humidity training data and concrete strength training data. The temperature and humidity data correspond to the concrete strength data, i.e., temperature-humidity-strength;
[0032] Step 2: The model is obtained by training the training set, and the concrete temperature and humidity training data in the test set are input into the model to output the concrete strength prediction result;
[0033] Step 3: Compare the concrete strength prediction result with the concrete strength verification data in the verification set to obtain the concrete strength prediction error, adjust the weight and threshold according to the error, repeat the forward calculation and reverse feedback, and gradually obtain the model structure and optimal solution consistent with the output result;
[0034] The training of BP neural network includes the forward propagation of signal and the reverse feedback of error:
[0035] Forward propagation: The signal enters the hidden layer after parallel weighted calculation from the input layer, and then enters the output layer after weighted processing to obtain the output;
[0036] Reverse feedback: It is carried out from the output to the input direction. The weights and thresholds are adjusted according to the actual error. By repeating forward calculation and reverse feedback, the model structure and optimal solution consistent with the output result are obtained.
[0037] The input n of the i-th node in the hidden layer during the forward propagation process i and output o i The calculation formula is as follows:
[0038]
[0039]
[0040] The input net of the kth node in the output layer during forward propagation k and output k The calculation formula is as follows:
[0041]
[0042]
[0043] Among them, w ij is the weight of the jth input variable in the i-th node of the hidden layer; φ is the activation function of the hidden layer; Ψ is the activation function of the output layer;
[0044] The error function E of the Pth sample p As shown in the following formula, where T k is the expected output value of the kth node:
[0045]
[0046] The total error E of P training samples is:
[0047]
[0048] In the feedback process, the weight correction amount and threshold correction amount of the hidden layer and the output layer are shown in the following formula, where η is the coefficient that determines the adjustment rate:
[0049]
[0050] The beneficial effects of the present invention are as follows: monitoring personnel can view the concrete temperature and humidity of the bridge and the current concrete strength data in real time, and issue a warning when the temperature value exceeds the limit. The actual operator on site can adjust the curing method according to the temperature item exceeding the limit, speed up the water circulation in and out, or sprinkle water on the surface of the pedestal. This makes up for the shortcomings of the traditional wired monitoring system, which is high cost and low efficiency. BRIEF DESCRIPTION OF THE DRAWINGS
[0051] 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:
[0052] Figure 1 It is a flow chart;
[0053] Figure 2 It is a schematic diagram of the prediction model structure;
[0054] Figure 3 This is a schematic diagram of the model prediction process;
[0055] Figure 4 It is a schematic diagram of the acquisition process of the lower computer module;
[0056] Figure 5 This is a schematic diagram of the host computer module acquisition process. DETAILED DESCRIPTION
[0057] In order to make the technical solutions and advantages in the embodiments of the present application more clearly understood, the exemplary embodiments of the present application are further described in detail below in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than an exhaustive list of all the embodiments. It should be noted that the embodiments in the present application and the features in the embodiments can be combined with each other without conflict.
[0058] Example 1, reference Figure 1-Figure 5 This embodiment describes a method for predicting the strength of large-volume concrete based on LoRa. The lower computer module collects concrete temperature and humidity data and transmits the collected data to the upper computer module. The upper computer module establishes a concrete strength prediction model of a BP neural network based on the concrete temperature and humidity data and the concrete strength data and outputs the concrete strength prediction result.
[0059] The lower computer module acquisition process includes the following steps:
[0060] S110. Arrange measurement points at one quarter of the base, and use 8 temperature and humidity sensors to measure the ambient temperature, maximum temperature, peak temperature, surface temperature, bottom temperature, water inlet temperature, water outlet temperature and center temperature respectively.
[0061] S120. Configuration module, the LoRa communication module uses the fixed-point transparent transmission function, configures the lower computer acquisition module and the corresponding upper computer module with the same module address, adjusts the airspeed to 0.3K, and configures the temperature acquisition card with a different module address;
[0062] S130. Configure the host computer module debugging interface, fill in the route and the base part, record the time point of cooling water injection into the mass concrete, input the mold temperature value, input parameter alarm threshold and input center temperature;
[0063] S140. Read the temperature data collected by the temperature acquisition card, turn on the power of the acquisition card and the temperature probe, use the RS485 bus to send a read command to the temperature acquisition card, send the device number, function number, register address, number of registers and calculate the CRC check code according to the MOBBUSRTU protocol, read the data returned by the temperature acquisition card after sending the command, use the CRC check to verify whether the correct data format is received, and extract the temperature of each sampling point in the received data;
[0064] S150. After receiving the data, determine whether the data acquisition card is working normally. When the temperature acquisition card cannot collect data, disconnect the power of all temperature probes and connect them one by one, disconnect the power of the damaged measuring point, connect the normal measuring point, and turn off the power of the peripheral after re-reading the normal data;
[0065] S160. Use the LoRa wireless serial port module to send the collected data to the host computer module;
[0066] The host computer module acquisition process includes the following steps:
[0067] S220. Call VISA serial port resources to obtain a string containing data, format and scan the string, the first two letters represent the location of the temperature measuring point, obtain temperature information according to the location of the measuring point, remove the damaged measuring point according to the value after obtaining the temperature information, the value collected when the temperature probe fails to be powered is 85, and the value collected when the probe is damaged is 0, remove the above two values to obtain the correct value, and obtain the temperature of each measuring layer, the inlet and outlet water temperature, and the ambient temperature;
[0068] S230. Obtain all temperature data every ten minutes;
[0069] S240. All temperature measurement data of the top layer and the bottom layer are summed and averaged to obtain the top layer temperature and the bottom layer temperature, the maximum value of the middle layer temperature is taken as the highest temperature of the platform, and the change of the highest temperature is recorded. The maximum value of the highest temperature during the measurement process is the peak temperature. The center temperature is obtained from the middle layer data, and a center temperature change curve is drawn. The outlet water temperature is subtracted from the inlet water temperature to obtain the inlet and outlet water temperature difference, the maximum temperature is subtracted from the surface temperature to obtain the surface-inside temperature difference, and the surface temperature is subtracted from the ambient temperature to obtain the ring-surface temperature difference. The temperature is taken every four hours to calculate the center temperature change rate as the cooling rate;
[0070] S250. The top layer temperature, middle layer temperature and bottom layer temperature data are compared with the parameter alarm threshold. If the threshold is exceeded, an alarm is issued. If the threshold is not exceeded, the next step is executed.
[0071] S260. Input the temperature data of 8 sensor sites at a certain moment into the concrete flow rate prediction model of the BP neural network to output the concrete strength prediction result.
[0072] The lower computer module includes: a main control chip, a temperature acquisition card, a temperature and humidity sensor, a LoRa wireless serial port module and a relay module;
[0073] The main control chip includes a temperature acquisition card, a temperature and humidity sensor, a LoRa wireless serial port module and a relay module;
[0074] The main control chip is powered by 12V DC, and the two serial ports are connected to the wireless transmission module and the temperature acquisition card respectively; the 32-way IO port is used to control the relay;
[0075] The temperature acquisition card is connected to the temperature and humidity sensor, powered by a 24V DC power supply, with 12 temperature and humidity sensor inputs, connected to the temperature measuring probe, set a sampling frequency of 1Hz, connected to the serial port of the main control chip through the RS485 bus and the SP3485 chip, and uses the MODBUSRTU communication protocol for data interaction;
[0076] The temperature and humidity sensor is used for temperature measurement. The probe is connected to a three-core shielded wire and powered by a 5V power supply output by a temperature acquisition card. The temperature measurement range is 55°C to +125°C, and the measurement error is 1°C.
[0077] The relay module is connected to the temperature acquisition card via the RS485 bus, with a total of 34 channels, 32 of which are used to control the power supply of the temperature probe, one for controlling the power supply of the acquisition card, and one for controlling the power supply of 32 relays, using the 5V voltage output by D-50B for power supply;
[0078] The LoRa wireless serial port module is used to establish two-way communication between the upper computer module and the lower computer module; the power of the LoRa wireless serial port module is 1W, LoRa spread spectrum modulation and many-to-one network, using the 433MHz frequency band, and the custom channel specifies the data transmission direction;
[0079] The upper computer module is used to receive and display the data transmitted by the lower computer and the concrete strength prediction result.
[0080] The method for obtaining concrete strength data is as follows: collect the surface temperature (℃) data at a certain moment, record the duration of the temperature at this moment (h), and find the equivalent coefficient α corresponding to the surface temperature at this moment through the temperature corresponding equivalent coefficient table. T , the temperature duration and α at this moment T Substitute t = Σα T t T Calculate t and substitute t into D. The concrete strength f(N / mm 2 ).
[0081] The concrete strength prediction model of the BP neural network includes an input layer, a hidden layer 1, a hidden layer 2 and an output layer; t1...t n The temperature of 8 concrete points at multiple times and the calibrated strength of concrete are input to the input layer, and a nonlinear mapping relationship is constructed with the concrete strength data through the hidden layer, and the output layer outputs the concrete strength;
[0082] The concrete strength prediction model training process of the BP neural network is as follows:
[0083] The concrete strength prediction model consists of three parts: training set, test set, and validation set. The prediction process is divided into the following three steps:
[0084] Step 1: The training set includes concrete temperature and humidity training data and concrete strength training data. The temperature and humidity data correspond to the concrete strength data, i.e., temperature-humidity-strength;
[0085] Step 2: The model is obtained by training the training set, and the concrete temperature and humidity training data in the test set are input into the model to output the concrete strength prediction result;
[0086] Step 3: Compare the concrete strength prediction result with the concrete strength verification data in the verification set to obtain the concrete strength prediction error, adjust the weight and threshold according to the error, repeat the forward calculation and reverse feedback, and gradually obtain the model structure and optimal solution consistent with the output result;
[0087] The training of BP neural network includes the forward propagation of signal and the reverse feedback of error:
[0088] Forward propagation: The signal enters the hidden layer after parallel weighted calculation from the input layer, and then enters the output layer after weighted processing to obtain the output;
[0089] Reverse feedback: It is carried out from the output to the input direction. The weights and thresholds are adjusted according to the actual error. By repeating forward calculation and reverse feedback, the model structure and optimal solution consistent with the output result are obtained.
[0090] Reference Figure 2 In the figure, temperature and humidity are input quantities, the subscripts are the input quantity numbers, and the corresponding input layer nodes are intensity. The output quantity is the output quantity, the subscripts are the output quantity numbers, and the corresponding output layer nodes (θ1, θ2, ..., θ i ,…,θ q ) is the threshold introduced by the hidden layer, and the subscript is the hidden node number. There may be multiple hidden layers (a1, a2..., a k , …, a l ) is the threshold introduced by the output layer, the subscript is the output node number, and there is only one output layer in the neural network. ε is the error value.
[0091] The input n of the i-th node in the hidden layer during the forward propagation process i and output o i The calculation formula is as follows:
[0092]
[0093]
[0094] The input net of the kth node in the output layer during forward propagation k and output k The calculation formula is as follows:
[0095]
[0096]
[0097] Among them, w ij is the weight of the jth input variable in the i-th node of the hidden layer; φ is the activation function of the hidden layer; Ψ is the activation function of the output layer;
[0098] The error function E of the Pth sample p As shown in the following formula, where T k is the expected output value of the kth node:
[0099]
[0100] The total error E of P training samples is:
[0101]
[0102] In the feedback process, the weight correction amount and threshold correction amount of the hidden layer and the output layer are shown in the following formula, where η is the coefficient that determines the adjustment rate:
[0103]
[0104] Although the present invention has been described according to a limited number of embodiments, it will be apparent to those skilled in the art, with the benefit of the above description, that other embodiments may be envisioned within the scope of the invention thus described. In addition, it should be noted that the language used in this specification is selected primarily for readability and teaching purposes, rather than for explaining or defining the subject matter of the present invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the present invention is illustrative, not restrictive, with respect to the scope of the present invention, which is defined by the appended claims.
Claims
1. A method for predicting mass concrete strength based on LoRa, characterized in that: The lower computer module collects concrete temperature and humidity data and transmits the collected data to the upper computer module. The upper computer module establishes a concrete strength prediction model of a BP neural network based on the concrete temperature and humidity data and the concrete strength data and outputs the concrete strength prediction result. The lower computer module includes: a main control chip, a temperature acquisition card, a temperature and humidity sensor, a LoRa wireless serial port module and a relay module; The main control chip is respectively connected to the temperature acquisition card, the temperature and humidity sensor, the LoRa wireless serial port module and the relay module; The main control chip is powered by 12V DC, and the two serial ports are connected to the wireless transmission module and the temperature acquisition card respectively; the 32-way IO port is used to control the relay; The temperature acquisition card is connected to the temperature and humidity sensor, powered by a 24V DC power supply, with 12 temperature and humidity sensor inputs, connected to the temperature measuring probe, set a sampling frequency of 1Hz, connected to the serial port of the main control chip through the RS485 bus and the SP3485 chip, and uses the MODBUSRTU communication protocol for data interaction; The temperature and humidity sensor is used for temperature measurement. The probe is connected to a three-core shielded wire and powered by a 5V power supply output by a temperature acquisition card. The temperature measurement range is 55°C to +125°C, and the measurement error is 1°C. The relay module is connected to the temperature acquisition card via the RS485 bus, with a total of 34 channels, 32 of which are used to control the power supply of the temperature probe, one for controlling the power supply of the acquisition card, and one for controlling the power supply of 32 relays, using the 5V voltage output by D-50B for power supply; The LoRa wireless serial port module is used to establish two-way communication between the upper computer module and the lower computer module; the power of the LoRa wireless serial port module is 1W, LoRa spread spectrum modulation and many-to-one network, using the 433MHz frequency band, and the custom channel specifies the data transmission direction; The upper computer module is used to receive and display the data transmitted by the lower computer and the concrete strength prediction result; The concrete strength prediction model of the BP neural network includes an input layer, a hidden layer 1, a hidden layer 2 and an output layer; t1...t n The temperature of 8 concrete points at multiple times and the calibrated strength of concrete are input to the input layer, and a nonlinear mapping relationship is constructed with the concrete strength data through the hidden layer, and the output layer outputs the concrete strength; The concrete strength prediction model training process of the BP neural network is as follows: The concrete strength prediction model consists of three parts: training set, test set, and validation set. The prediction process is divided into the following three steps: Step 1: The training set includes concrete temperature and humidity training data and concrete strength training data. The temperature and humidity data correspond to the concrete strength data, i.e., temperature-humidity-strength; Step 2: The model is obtained by training the training set, and the concrete temperature and humidity training data in the test set are input into the model to output the concrete strength prediction result; Step 3: Compare the concrete strength prediction result with the concrete strength verification data in the verification set to obtain the concrete strength prediction error, adjust the weight and threshold according to the error, repeat the forward calculation and reverse feedback, and gradually obtain the model structure and optimal solution consistent with the output result; The training of BP neural network includes the forward propagation of signal and the reverse feedback of error: Forward propagation: The signal enters the hidden layer after parallel weighted calculation from the input layer, and then enters the output layer after weighted processing to obtain the output; Reverse feedback: It is carried out from the output to the input direction. The weights and thresholds are adjusted according to the actual error. By repeating forward calculation and reverse feedback, the model structure and optimal solution consistent with the output result are obtained. The input n of the i-th node in the hidden layer during the forward propagation process i and output o i The calculation formula is as follows: The input net of the kth node in the output layer during forward propagation k and output k The calculation formula is as follows: Among them, w ij is the weight of the jth input variable in the i-th node of the hidden layer; φ is the activation function of the hidden layer; Ψ is the activation function of the output layer; The error function E of the Pth sample p As shown in the following formula, where T k is the expected output value of the kth node: The total error E of P training samples is: In the feedback process, the weight correction amount and threshold correction amount of the hidden layer and the output layer are shown in the following formula, where η is the coefficient that determines the adjustment rate:
2. A method for predicting mass concrete strength based on LoRa according to claim 1, characterized in that: The method for obtaining concrete strength data is as follows: collect the surface temperature (℃) data at a certain moment, record the duration of the temperature at this moment (h), and find the equivalent coefficient α corresponding to the surface temperature at this moment through the temperature corresponding equivalent coefficient table. T , the temperature duration and α at this moment T Substitute t = ∑α T t T Calculate t and substitute t into D. The concrete strength f(N / mm 2 ).
3. A method for predicting mass concrete strength based on LoRa according to claim 2, characterized in that: The lower computer module acquisition process includes the following steps: S110. Arrange measurement points at one quarter of the platform, and use 8 temperature and humidity sensors to measure the ambient temperature, maximum temperature, peak temperature, surface temperature, bottom temperature, water inlet temperature, water outlet temperature and center temperature respectively; S120. Configuration module, the LoRa communication module uses the fixed-point transparent transmission function, configures the lower computer acquisition module and the corresponding upper computer module with the same module address, adjusts the airspeed to 0.3K, and configures the temperature acquisition card with a different module address; S130. Configure the host computer module debugging interface, fill in the route and the base part, record the time point of cooling water injection into the mass concrete, input the mold temperature value, input parameter alarm threshold and input center temperature; S140. Read the temperature data collected by the temperature acquisition card, turn on the power of the acquisition card and the temperature probe, use the RS485 bus to send a read command to the temperature acquisition card, send the device number, function number, register address, number of registers and calculate the CRC check code according to the MOBBUS RTU protocol, read the data returned by the temperature acquisition card after sending the command, use the CRC check to verify whether the correct data format is received, and extract the temperature of each sampling point in the received data; S150. After receiving the data, determine whether the data acquisition card is working normally. When the temperature acquisition card cannot collect data, disconnect the power of all temperature probes and connect them one by one, disconnect the power of the damaged measuring point, connect the normal measuring point, and turn off the power of the peripheral after re-reading the normal data; S160. Use the LoRa wireless serial port module to send the collected data to the host computer module.
4. A method for predicting mass concrete strength based on LoRa according to claim 3, characterized in that: The host computer module acquisition process includes the following steps: S220. Call VISA serial port resources to obtain a string containing data, format and scan the string, the first two letters represent the location of the temperature measuring point, obtain temperature information according to the location of the measuring point, remove the damaged measuring point according to the value after obtaining the temperature information, the value collected when the temperature probe fails to be powered is 85, and the value collected when the probe is damaged is 0, remove the above two values to obtain the correct value, and obtain the temperature of each measuring layer, the inlet and outlet water temperature, and the ambient temperature; S230. Obtain all temperature data every ten minutes; S240. All temperature measurement data of the top layer and the bottom layer are summed and averaged to obtain the top layer temperature and the bottom layer temperature, the maximum value of the middle layer temperature is taken as the highest temperature of the platform, and the change of the highest temperature is recorded. The maximum value of the highest temperature during the measurement process is the peak temperature. The center temperature is obtained from the middle layer data, and a center temperature change curve is drawn. The outlet water temperature is subtracted from the inlet water temperature to obtain the inlet and outlet water temperature difference, the maximum temperature is subtracted from the surface temperature to obtain the surface-inside temperature difference, and the surface temperature is subtracted from the ambient temperature to obtain the ring-surface temperature difference. The temperature is taken every four hours to calculate the center temperature change rate as the cooling rate; S250. The top layer temperature, middle layer temperature and bottom layer temperature data are compared with the parameter alarm threshold. If the threshold is exceeded, an alarm is issued. If the threshold is not exceeded, the next step is executed. S260. Input the temperature data of 8 sensor sites at a certain moment into the concrete flow rate prediction model of the BP neural network to output the concrete strength prediction result.
