Intelligent control high-temperature test device and test method

Abstract

The invention provides an intelligent control high-temperature test device and method, and belongs to the technical field of high temperature, the intelligent control high-temperature test device comprises a test furnace and intelligent equipment, a temperature sensor, a heating element, a control system and a cooling system are arranged in the test furnace, and the temperature sensor, the heating element and the cooling system are connected with the control system; the control system is connected with the intelligent device through a network. Intellectualization of the test furnace is achieved, control parameters can be remotely set, test data can be uploaded in real time, and the system objectively observes the test heating and cooling process and the like. The problems that a traditional test electric furnace is prone to pipe disengaging, remote control cannot be achieved, faults are not prone to being found, operation is inconvenient, and test parameters are inaccurate are solved, and the device has important significance on guaranteeing the safety and reliability of a high-temperature test. According to the invention, control parameters can be remotely set, data such as actual temperature can be remotely checked, the test heating and cooling process can be systematically and objectively observed, the working efficiency and the test accuracy are improved, and the test safety risk is reduced.

Description

Technical Field

[0001] The invention relates to the field of high temperature technology, and in particular to an intelligent control high temperature test device and a test method. Background Art

[0002] High temperature electric furnace is one of the important equipment in high temperature processing industry. Its function is to heat the sample to the required temperature, keep it warm and cool it. Traditional high temperature electric furnace is usually composed of temperature sensor, heating element, control system and cooling system. The control system detects the temperature of the sample through the temperature sensor and controls the heating element according to the set temperature to achieve the functions of heating and keeping warm. After the test, the cooling system will cool down according to the program setting.

[0003] At present, most of the traditional high-temperature electric furnaces are used in China. During use, test personnel cannot control the test furnace anytime and anywhere. They need to go to the laboratory regularly to observe the equipment and test conditions. It is easy for the equipment to be disconnected at night. At the same time, the operation is not convenient. Various command parameters need to be manually input, which is prone to errors. If a malfunction occurs during the equipment test, the test personnel generally cannot discover it in time, which poses a safety hazard. The test personnel cannot accurately judge whether the various parameters of the high-temperature electric furnace during the test heating process meet the test standards or customer requirements. Summary of the invention

[0004] The present invention provides an intelligent control high temperature test device and test method, which realizes the intelligence of the test furnace, can remotely set control parameters and upload data such as actual temperature in real time, and the system objectively observes the test heating and cooling process. It solves the problems of traditional test furnaces that are easy to detach tubes, cannot be remotely controlled, are difficult to find faults, are inconvenient to operate, and have inaccurate test parameters.

[0005] The present invention provides the following technical solutions:

[0006] An intelligent controlled high temperature test device comprises a test furnace and an intelligent device. The test furnace is provided with a temperature sensor, a heating element, a control system and a cooling system. The temperature sensor, the heating element and the cooling system are connected to the control system, and the control system is connected to the intelligent device via a network.

[0007] Furthermore, the furnace body of the test furnace includes a double-layer air curtain furnace shell, the interior of the double-layer air curtain furnace shell is filled with a polycrystalline fiber lining, the temperature sensor is a B-type double platinum-rhodium thermocouple, the temperature rising range of the test furnace is 100~1700℃, the control system includes a single board computer, and the single board computer includes an Ethernet interface.

[0008] A test method for an intelligently controlled high temperature test device, comprising:

[0009] Place the sample into the test furnace;

[0010] The intelligent device obtains the test instruction and sends a control signal containing the test instruction to the control system of the test furnace; wherein the test instruction includes a heating curve and a cooling curve;

[0011] The control system receives the control signal and automatically sets the temperature increase program and the temperature decrease program according to the received control signal;

[0012] The control system automatically controls the heating element and cooling system according to the set heating program and cooling program, and starts the high temperature test;

[0013] During the high temperature test, the control system uploads the test data to the smart device in real time through the network;

[0014] The test personnel check the test data through smart devices;

[0015] After the high temperature test is completed, take out the sample.

[0016] Furthermore, the smart device includes a browsing module, through which the test personnel input test instructions by voice or manually, and view test data through the browsing module.

[0017] Furthermore, the heating curve and cooling curve include the maximum test temperature, heating rate, heating time, insulation temperature, insulation time, cooling rate and cooling time, and the test data include actual temperature, set temperature, actual heating rate, actual cooling rate, and the test time and remaining time of each section of the heating section, insulation section and cooling section.

[0018] Furthermore, the method further comprises:

[0019] During the high-temperature test, if any abnormality is found, the test personnel will send a stop test command to the control system through the intelligent device; the control system will receive the stop test command and stop the high-temperature test.

[0020] Furthermore, the method further comprises:

[0021] After the high temperature test is completed, the intelligent device prompts the end of the high temperature test, and saves the actual heating curve and actual cooling curve during the high temperature test, and automatically evaluates whether the high temperature test process meets the test requirements.

[0022] Furthermore, the sample is a refractory material sample, and the intelligent device obtains a test instruction and sends a control signal containing the test instruction to a control system of the test furnace, including:

[0023] The tester inputs the parameters of the refractory material sample into the smart device by voice or manually, wherein the parameters include the material and size of the refractory material sample and the performance to be achieved by the refractory material sample;

[0024] The intelligent device calls a pre-trained neural network model, and the neural network model automatically generates a test instruction according to the input parameters of the refractory material sample; wherein the test instruction includes a heating curve and a cooling curve;

[0025] The intelligent device sends control signals to the control system based on the automatically generated test instructions.

[0026] Furthermore, the neural network model is trained by the following method:

[0027] Build a neural network model;

[0028] Establishing a training set, wherein the training set includes a plurality of training samples, each training sample includes parameters of a refractory material sample, and each training sample is provided with a corresponding label, wherein the label is an optimal heating curve and an optimal cooling curve known for the training sample;

[0029] A batch of training samples is randomly selected from the training set, and the selected batch of training samples is input into the neural network model to predict the heating curve and cooling curve of each training sample, and the training error is calculated according to the predicted heating curve and cooling curve and the best heating curve and cooling curve contained in the label, and the parameters of the neural network are updated according to the training error;

[0030] Select the next batch of training samples and continue training the neural network model until the training termination condition is reached.

[0031] The present invention has the following beneficial effects:

[0032] The present invention realizes the intelligence of the test furnace, and can remotely set control parameters, upload test data in real time, and systematically and objectively observe the test heating and cooling process. It solves the problems of traditional test furnaces that are easy to detach tubes, cannot be remotely controlled, faults are difficult to find, operation is inconvenient, and test parameters are inaccurate. It is of great significance to ensure the safety and reliability of high-temperature tests. In addition, the present invention is safe and reliable, low cost, and the test method is simple to operate. For test device manufacturers, it is beneficial to improve product quality and save social resources. For test device users, they can remotely set control parameters, remotely view test data such as actual temperature, and systematically and objectively observe the test heating and cooling process, thereby improving work efficiency and test accuracy and reducing test safety risks. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 It is a schematic diagram of the intelligent control high temperature test device of the present invention;

[0034] Figure 2 This is a schematic diagram of the structure of the test furnace. DETAILED DESCRIPTION

[0035] In order to make the technical problems, technical solutions and advantages to be solved by the present invention more clear, a detailed description will be given below with reference to the accompanying drawings and specific embodiments.

[0036] The embodiment of the present invention provides an intelligent control high temperature test device, such as Figure 1-2 As shown, it includes a test furnace 1 and an intelligent device 2. A temperature sensor 3, a heating element 4, a control system 5 and a cooling system 6 are arranged in the test furnace 1. The temperature sensor 3, the heating element 4 and the cooling system 6 are connected to the control system 5, and the control system 5 is connected to the intelligent device 2 through a network.

[0037] It is crucial that the present invention combines intelligent control technology with traditional high-temperature electric furnaces to perform intelligent control of high-temperature electric furnaces. Test personnel can remotely set control parameters through smart devices and view test data such as actual temperature uploaded in real time through smart devices.

[0038] The present invention realizes the intelligence of the test furnace, and can remotely set control parameters, upload test data in real time, and systematically and objectively observe the test heating and cooling process. It solves the problems of traditional test furnaces that are easy to detach tubes, cannot be remotely controlled, faults are difficult to find, operation is inconvenient, and test parameters are inaccurate. It is of great significance to ensure the safety and reliability of high-temperature tests. In addition, the present invention is safe and reliable, low cost, and the test method is simple to operate. For test device manufacturers, it is beneficial to improve product quality and save social resources. For test device users, they can remotely set control parameters, remotely view test data such as actual temperature, and systematically and objectively observe the test heating and cooling process, thereby improving work efficiency and test accuracy and reducing test safety risks.

[0039] The test furnace 1 of the present invention adopts a floor-standing structure, and its furnace body includes a double-layer air curtain furnace shell, and the double-layer air curtain furnace shell is filled with a polycrystalline fiber furnace lining. The temperature sensor 3 is a B-type double platinum-rhodium thermocouple. The temperature rise range of the test furnace 1 is 100-1700°C. The heating element 4 can be replaced according to the test requirements. The control system 5 includes a single board computer, and the single board computer includes an Ethernet interface to achieve remote connection with smart devices.

[0040] The smart device 2 can be a mobile phone, computer, tablet computer, local server, cloud service system and other intelligent devices. It is equipped with corresponding software, such as a browser module.

[0041] The embodiment of the present invention also provides a test method of the above-mentioned intelligent control high temperature test device, the method comprising:

[0042] S1: Place the sample into the test furnace, close the furnace door, and keep the test furnace sealed.

[0043] S2: The intelligent device obtains the test instruction and sends a control signal containing the test instruction to the control system of the test furnace; wherein the test instruction includes a heating curve and a cooling curve.

[0044] The test personnel can input the test instructions manually or by voice input. The intelligent device generates control signals according to the input test instructions and sends them to the control system.

[0045] The test instructions may include a heating curve and a cooling curve, specifically including: the maximum test temperature, heating rate, heating time, holding temperature, holding time, cooling rate and cooling time, etc.

[0046] S3: The control system receives the control signal and automatically sets the heating program and the cooling program according to the received control signal.

[0047] S4: The control system automatically controls the heating element and cooling system according to the set heating program and cooling program, and starts the high temperature test.

[0048] S5: During the high temperature test, the control system uploads the test data to the smart device in real time through the network.

[0049] S6: The test personnel view the test data through smart devices.

[0050] Specifically, the intelligent device includes a browsing module, through which the test personnel can input test instructions by voice or manually, and view test data through the browsing module.

[0051] The test data includes actual temperature, set temperature, test time and remaining time of each section of heating section, insulation section and cooling section, actual heating rate, actual cooling rate, etc. It is simple to operate, accurate and reliable, intelligent and efficient, and can intuitively observe the test process.

[0052] S7: After the high temperature test is completed, take out the sample.

[0053] As an improvement, the test method also includes:

[0054] During the high-temperature test, if any abnormality is found, the test personnel will send a stop test command to the control system through the intelligent device; the control system will receive the stop test command and stop the high-temperature test.

[0055] After the high temperature test is completed, the intelligent device will prompt the end of the high temperature test, and automatically save the heating curve and cooling curve during the high temperature test, and automatically evaluate whether the test process meets the test requirements.

[0056] In the process of developing new refractory products, after determining the formula of the refractory materials, the refractory materials are made into samples of different sizes and then fired in a kiln. During the firing process, it is necessary to determine the heating and cooling procedures based on the expected performance of the refractory materials. The existing technology generally determines the heating and cooling procedures through manual experience, which makes it difficult to make the refractory samples fully react and achieve the best performance. Moreover, kilns are generally used for large-scale firing, but when developing new refractory products, they are all small-batch tests. Firing in a kiln is not only inconvenient, but also wasteful.

[0057] To solve the above problems, the present invention uses the test furnace 1 in the process of developing new refractory products. The refractory samples are fired in small batches through the test furnace 1. When the required performance is achieved, the research and development is completed, and the refractory products are fired on a large scale through the kiln.

[0058] Specifically, the steps include:

[0059] S21: The tester inputs the parameters of the refractory material sample into the smart device by voice or manually. The parameters include the material and size of the refractory material sample and the performance to be achieved by the refractory material sample.

[0060] S22: The intelligent device calls a pre-trained neural network model, and the neural network model automatically generates test instructions according to the input parameters of the refractory material sample; wherein the test instructions include a heating curve and a cooling curve.

[0061] S23: The intelligent device sends a control signal to the control system according to the automatically generated test instruction.

[0062] The present invention combines the neural network model with the test furnace. In addition to realizing remote control, the test furnace can also be used to develop new refractory products. Specifically, after the test furnace learns based on a large amount of existing data, through model calculation, the test furnace can automatically analyze and design the heating curve and cooling curve according to the material and size of the refractory sample to be developed, and according to the physical properties or chemical properties results desired by the user, automatically complete the heating process and the cooling process, and allow the refractory sample to fully react to achieve the best physical and chemical properties.

[0063] The neural network model needs to be trained before deployment. The training method is as follows:

[0064] 1. Build a neural network model.

[0065] 2. Establish a training set, which includes multiple training samples, each training sample includes parameters of a refractory material sample, and each training sample is provided with a corresponding label, which is the best heating curve and the best cooling curve known for the training sample.

[0066] The samples of the training set should include as many types of refractory samples as possible, and cover refractory samples of different material formulas and sizes as widely as possible. When constructing the training set, it is necessary to obtain multiple refractory samples and their corresponding optimal heating curves and optimal cooling curves in advance as training data.

[0067] 3. Randomly select a batch of training samples from the training set, and input the selected batch of training samples into the neural network model to predict the heating curve and cooling curve of each training sample. Calculate the training error based on the predicted heating curve and cooling curve and the best heating curve and cooling curve contained in the label, and update the parameters of the neural network based on the training error.

[0068] The training of the neural network model includes forward propagation and back propagation processes. Forward propagation is to extract features based on the training samples and obtain the estimated heating curve and cooling curve based on the features. Back propagation is to learn the algorithm based on the estimated heating curve and cooling curve and the best heating curve and cooling curve contained in the label, and continuously adjust the network weights according to the error of the back propagation result.

[0069] 4. Select the next batch of training samples and continue training the neural network model until the training termination condition is reached.

[0070] The training termination condition may be that the set number of training times has been reached, or the error of the back propagation result is less than the set threshold, or the training has reached the set time, etc.

[0071] The above is a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An intelligent controlled high temperature test device, characterized in that: The invention comprises a test furnace and an intelligent device. The test furnace is provided with a temperature sensor, a heating element, a control system and a cooling system. The temperature sensor, the heating element and the cooling system are connected with the control system. The control system is connected with the intelligent device via a network.

2. The intelligent control high temperature test device according to claim 1 is characterized in that: The furnace body of the test furnace includes a double-layer air curtain furnace shell, the interior of the double-layer air curtain furnace shell is filled with a polycrystalline fiber furnace lining, the temperature sensor is a B-type double platinum-rhodium thermocouple, the temperature rising range of the test furnace is 100~1700℃, the control system includes a single board computer, and the single board computer includes an Ethernet interface.

3. A test method for the intelligent controlled high temperature test device according to claim 1 or 2, characterized in that: include: Place the sample into the test furnace; The intelligent device obtains the test instruction and sends a control signal containing the test instruction to the control system of the test furnace; wherein the test instruction includes a heating curve and a cooling curve; The control system receives the control signal and automatically sets the temperature increase program and the temperature decrease program according to the received control signal; The control system automatically controls the heating element and cooling system according to the set heating program and cooling program, and starts the high temperature test; During the high temperature test, the control system uploads the test data to the smart device in real time through the network; The test personnel check the test data through smart devices; After the high temperature test is completed, take out the sample.

4. The test method according to claim 3, characterized in that The smart device includes a browsing module, through which the test personnel input the test instructions by voice or manually, and view the test data through the browsing module.

5. The test method according to claim 3, characterized in that: The heating curve and cooling curve include the maximum test temperature, heating rate, heating time, insulation temperature, insulation time, cooling rate and cooling time; the test data include actual temperature, set temperature, actual heating rate, actual cooling rate, and the test time and remaining time of each section of the heating section, insulation section and cooling section.

6. The test method according to claim 5, characterized in that The method further comprises: During the high-temperature test, if any abnormality is found, the test personnel will send a stop test command to the control system through the intelligent device; the control system will receive the stop test command and stop the high-temperature test.

7. The test method according to claim 6, characterized in that: The method further comprises: After the high temperature test is completed, the intelligent device prompts the end of the high temperature test, and saves the actual heating curve and actual cooling curve during the high temperature test, and automatically evaluates whether the high temperature test process meets the test requirements.

8. The test method according to claim 3, characterized in that: The sample is a refractory material sample, and the intelligent device obtains a test instruction and sends a control signal containing the test instruction to the control system of the test furnace, including: The tester inputs the parameters of the refractory material sample into the smart device by voice or manually, wherein the parameters include the material and size of the refractory material sample and the performance to be achieved by the refractory material sample; The intelligent device calls a pre-trained neural network model, and the neural network model automatically generates a test instruction according to the input parameters of the refractory material sample; wherein the test instruction includes a heating curve and a cooling curve; The intelligent device sends control signals to the control system based on the automatically generated test instructions.

9. The test method according to claim 8, characterized in that The neural network model is trained by the following method: Build a neural network model; Establishing a training set, wherein the training set includes a plurality of training samples, each training sample includes parameters of a refractory material sample, and each training sample is provided with a corresponding label, wherein the label is an optimal heating curve and an optimal cooling curve known for the training sample; A batch of training samples is randomly selected from the training set, and the selected batch of training samples is input into the neural network model to predict the heating curve and cooling curve of each training sample, and the training error is calculated according to the predicted heating curve and cooling curve and the best heating curve and cooling curve contained in the label, and the parameters of the neural network are updated according to the training error; Select the next batch of training samples and continue training the neural network model until the training termination condition is reached.

Images