Scraper state real-time detection system and method

Abstract

The invention relates to a scraper state real-time detection system and method, and the method comprises the following steps: installing a resistance sensor in a scraper, and detecting the resistance data of the scraper in the working process in real time through the resistance sensor; in the shield tunneling process, cutterhead rotating speed data, cutterhead angle data and feed rate data are collected in real time; inputting the cutterhead rotating speed data, the cutterhead angle data, the feed rate data and the resistance data into an intelligent module; the scraper abrasion loss, the scraper perfectness ratio and the scraper predicted service life output by the intelligent module are received and displayed. The abrasion condition of the scraper is detected through the resistance sensor, the abrasion loss of the scraper can be obtained through conversion according to resistance data detected by the resistance sensor, and the abrasion condition of the scraper is accurately represented.

Description

Technical Field

[0001] The invention relates to the technical field of shield construction, and in particular to a real-time detection system and method for scraper status. Background Art

[0002] In the prior art, direct detection methods are usually used to detect the wear of shield scrapers. The direct detection method specifically uses the hydraulic sensor system in the cutter disc to detect the leaked hydraulic oil to judge the wear state of the scraper, because once the scraper is worn to a certain extent, the hydraulic oil will flow out. The hydraulic sensor method is widely used in the wear detection of scrapers and cutter disc surfaces because of its simple principle, convenient maintenance and low cost. Its disadvantage is that the hydraulic sensor method measures a fixed value of wear, and the scraper should be replaced when this value is reached. The hydraulic sensor method has a certain hysteresis in measuring wear and is not accurate enough, and it is impossible to measure the wear value of the tool in real time. The layout of hydraulic sensors mostly relies on experience and cannot accurately characterize the overall wear of regional tools. It is very likely to cause multiple openings and tool changes, reducing construction efficiency. Summary of the invention

[0003] The purpose of the present invention is to overcome the defects of the prior art and provide a real-time detection system and method for the scraper status to solve the problem that the existing hydraulic sensor method has hysteresis and lacks precision in measurement, and cannot measure the wear value of the tool in real time, which leads to multiple openings and tool changes, reducing construction efficiency.

[0004] The technical solution to achieve the above purpose is:

[0005] The present invention provides a method for real-time detection of scraper status, comprising the following steps:

[0006] A resistance sensor is installed in the scraper, and the resistance data of the scraper during operation is detected in real time by the resistance sensor;

[0007] During the shield tunneling process, the cutter head speed data, cutter head angle data and feed rate data are collected in real time;

[0008] Inputting the cutter head speed data, cutter head angle data, cutter feed rate data and resistance data into an intelligent module;

[0009] The scraper wear amount, scraper integrity rate and scraper predicted life output by the intelligent module are received and displayed.

[0010] A further improvement of the scraper state real-time detection method of the present invention is that it also includes:

[0011] In the early stage of shield tunneling construction, construction parameters within a set distance are selected as training data. The selected construction parameters include resistance data, cutter head speed data, cutter head angle data, and feed rate data.

[0012] Calculating and obtaining corresponding constraint results using the construction parameters;

[0013] The training data and the corresponding constraint results are subjected to model training of a corresponding machine learning algorithm to obtain an intelligent module.

[0014] A further improvement of the real-time scraper status detection method of the present invention is that before the cutter disc speed data, cutter disc angle data, feed rate data and resistance data are input into an intelligent module, the cutter disc speed data, cutter disc angle data, feed rate data and resistance data are filtered and cleaned.

[0015] A further improvement of the real-time scraper status detection method of the present invention is that it also includes: storing the cutter disc speed data, cutter disc angle data, feed rate data and resistance data in a database.

[0016] The present invention also provides a scraper state real-time detection system, comprising:

[0017] The resistance sensor installed in the scraper is used to detect the resistance data in real time during the operation of the scraper;

[0018] Construction data acquisition unit, used to collect cutter head speed data, cutter head angle data and feed rate data in real time during shield tunneling;

[0019] A data platform connected to the resistance sensor and the construction data acquisition unit, used to receive the resistance data detected by the resistance sensor in real time and the cutter head speed data, cutter head angle data and feed rate data collected by the construction data acquisition unit in real time;

[0020] An intelligent module connected to the data platform, the intelligent module is used to receive the resistance data, the cutter head speed data, the cutter head angle data and the feed rate data sent by the data platform, and output the corresponding scraper wear amount, scraper integrity rate and scraper predicted life to the data platform;

[0021] The display unit connected to the data platform is used to display the scraper wear amount, scraper integrity rate and scraper predicted life sent by the data platform.

[0022] A further improvement of the scraper state real-time detection system of the present invention is that the intelligent module is obtained by model training using a machine learning algorithm, and the training data for the model training is the construction parameters collected within a set distance in the early stage of shield tunneling construction, and the construction parameters include resistance data, cutter head speed data, cutter head angle data, and feed rate data;

[0023] The training data also includes constraint results calculated based on the construction parameters.

[0024] A further improvement of the scraper status real-time detection system of the present invention is that the data platform filters and cleans the resistance data, cutter disc speed data, cutter disc angle data and feed rate data before sending the resistance data, cutter disc speed data, cutter disc angle data and feed rate data to the intelligent module.

[0025] A further improvement of the scraper status real-time detection system of the present invention is that it also includes a database connected to the data platform, and the database is used to store the cutter disc speed data, cutter disc angle data, feed rate data and resistance data.

[0026] The beneficial effects of the scraper status real-time detection system and method of the present invention are:

[0027] The present invention detects the wear condition of the scraper by means of a resistance sensor, and the wear amount of the scraper can be converted according to the resistance data detected by the resistance sensor, thereby achieving accurate characterization of the wear condition of the scraper.

[0028] The intelligent module of the present invention can learn the scraper wear data and construction data through a machine learning algorithm, so as to predict the working life of the scraper.

[0029] The scraper wear amount, scraper integrity rate and predicted scraper life of the present invention can be displayed visually, so as to realize efficient monitoring of the scraper and establish a reasonable and accurate tool management plan. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is a system diagram of the scraper status real-time detection system of the present invention.

[0031] Figure 2 It is a structural schematic diagram of a resistance sensor arranged on a blade disc in the real-time detection system and method of the scraper status of the present invention.

[0032] Figure 3 It is a structural schematic diagram of a resistance sensor arranged on a scraper in the real-time scraper status detection system and method of the present invention. DETAILED DESCRIPTION

[0033] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments.

[0034] See also Figure 1 The present invention provides a real-time detection system and method for scraper status, which is used to solve the hysteresis and accuracy problems of real-time detection of shield scraper wear. The scraper wear can be monitored in real time and the working life of the scraper can be predicted to help establish a reasonable and accurate tool management system. The real-time detection system and method for scraper status of the present invention are described below in conjunction with the accompanying drawings.

[0035] See also Figure 1 , showing the system diagram of the scraper status real-time detection system of the present invention. Figure 1 , the real-time detection system of scraper status of the present invention is explained.

[0036] like Figure 1 As shown, the scraper status real-time detection system of the present invention includes a resistance sensor, a construction data acquisition unit, a data platform, an intelligent module and a display unit, wherein the resistance sensor is arranged in the scraper, and the resistance sensor is used to detect the resistance data in real time during the operation of the scraper; the construction data acquisition unit is used to collect the cutter head speed data, the cutter head angle data and the feed rate data in real time during the shield tunneling process; the data platform is connected with the resistance sensor and the construction data acquisition unit, and the data platform is used to receive the resistance data detected in real time by the resistance sensor and the cutter head speed data, the cutter head angle data and the feed rate data collected in real time by the construction data acquisition unit; the intelligent module is connected with the data platform, and the intelligent module is used to receive the resistance data, the cutter head speed data, the cutter head angle data and the feed rate data sent by the data platform, and output the corresponding scraper wear amount, the scraper intact rate and the scraper predicted life to the data platform; the display unit is connected with the data platform, and the display unit is used to display the scraper wear amount, the scraper intact rate and the scraper predicted life sent by the data platform.

[0037] In a specific embodiment of the present invention, the intelligent module is obtained by model training using a machine learning algorithm, and the training data for the model training are the construction parameters collected within a set distance in the early stage of shield tunneling construction, and the construction parameters include resistance data, cutter head speed data, cutter head angle data, and feed rate data; the training data also includes constraint results calculated based on the construction parameters.

[0038] The constraint results calculated based on the construction parameters include scraper wear, scraper integrity rate and scraper predicted life.

[0039] The intelligent module uses edge computing and is pre-installed with intelligent algorithms such as machine learning. After acquiring data, it calculates the working status of the tool. It mainly calculates core indicators such as tool wear and intactness, and predicts the working life.

[0040] The training data can be selected from the construction parameters within a set distance in the early stage of the shield machine excavation construction. The set distance can be a distance of 50, 80 or 100 rings before the excavation construction. The construction parameters within the set distance, the detected resistance data and the corresponding constraint results are used as training data, so that the intelligent model can learn to output the corresponding constraint results based on the input construction parameters and resistance data.

[0041] Furthermore, if Figure 3 As shown, the working principle of the resistor sensor 22 is to use the resistor row as the core component of the circuit board inside the sensor, connect them in parallel, and determine the design resistance value of each resistor through the pre-designed measurement accuracy and the linear relationship between the resistance value and the wear amount. The resistor row is placed in the scraper 21, and the end of the resistor row will be worn accordingly as the scraper wears. The linear relationship between the total resistance value and the wear amount is monitored, and the change in the total resistance value is inferred, so as to calculate the wear degree of the tool. The synchronous detection of tool wear and sensor is realized at the principle level.

[0042] ΔR=(R×X) / L=K L ×X (1)

[0043] In formula (1), R is the total resistance of the sensor; X is the wear amount; the wear range of the sensor is 0 to L; KL is the resistance per unit length, which is a constant when the wire material is evenly distributed.

[0044] Furthermore, the tool integrity rate and the predicted life of the tool can be directly calculated based on the wear amount of the tool.

[0045] Furthermore, if Figure 2 As shown, multiple resistance sensors 22 are arranged on the cutter disc corresponding to the cutting track of the scraper, and two hydraulic wear detection points 23 are arranged on the cutting track of the outer periphery of the cutter disc. The detection results of the hydraulic wear detection points 23 are mutually verified with the detection results of the resistance sensors 22 to accurately judge whether the scraper needs to be replaced. Two hydraulic wear detection points are also arranged behind the wear-resistant plate of the cutter disc body to detect the wear-resistant plate and prevent it from being worn through.

[0046] In a specific embodiment of the present invention, the data platform filters and cleans the resistance data, the cutter disc speed data, the cutter disc angle data and the feed rate data before sending the resistance data, the cutter disc speed data, the cutter disc angle data and the feed rate data to the intelligent module.

[0047] Furthermore, it also includes a database connected to the data platform, and the database is used to store cutter disc speed data, cutter disc angle data, feed rate data and resistance data.

[0048] Furthermore, it also includes a filter database connected to the data platform, which is used to store the resistance data, cutter head speed data, cutter head angle data and feed rate data that have been filtered and cleaned. The filter database and database are set to achieve data backup and storage.

[0049] In a specific embodiment of the present invention, Figure 1 As shown, the system of the present invention also includes a data sending module, which is connected to the resistance sensor and receives resistance data detected by the resistance sensor. The data sending module is connected to the data platform via Bluetooth or a center rotary joint, and then the data sending module can send the resistance data to the data platform.

[0050] The resistance sensor installed on the tool has a built-in resistance value, and a resistor row is installed in the tool to measure the wear of the tool. The sensor module collects data from the resistance sensor installed on the tool and converts it into a standard data signal.

[0051] The construction data collection unit and the data platform can be connected via wired or wireless connection, and the collected cutter head speed, feed rate and cutter head angle can be sent to the data platform.

[0052] After receiving the data, the data platform sends the data to the data cleaning for cleaning and filtering. After cleaning and filtering, the data will be stored in the filtering database. The data platform will also directly send the received data to the original database for storage. The data platform can also send the data to the data service, and then the intelligent module will perform data mining to obtain the corresponding scraper wear, scraper integrity rate and scraper predicted life. The intelligent module will feed back the results to the data platform, and the data platform will send the feedback results to the data display unit for display.

[0053] The data platform of the present invention is based on the communication interface of SLMP, and can access the SLMP corresponding device and the programmable controller connected to the SLMP corresponding device through an external device. By sending a request message from the external device connected using Ethernet to the SLMP corresponding device and receiving a response message, not only can the soft elements be read, but also the soft elements can be written and the SLMP corresponding device can be reset.

[0054] The data platform is responsible for saving and backing up the collected data on the scraper working status and construction working status, and then filtering and cleaning the data. The cleaned data is sent by the data service to the intelligent module for data mining, and the data sent back by the intelligent module is received for visual display.

[0055] The database of the present invention adopts a time series modeless ingestion database, which is specially used for storing and managing time series. It has the characteristics of more writing and less reading, high concurrent writing, no transaction requirements, and continuous writing of massive data. It can be used for industrial manufacturing and system monitoring based on time interval aggregation analysis and efficient retrieval.

[0056] The present invention also provides a real-time detection method for the scraper status, which is described below.

[0057] like Figure 1 As shown, the detection method of the present invention comprises the following steps:

[0058] A resistance sensor is installed in the scraper, and the resistance data of the scraper during operation is detected in real time by the resistance sensor;

[0059] During the shield tunneling process, the cutter head speed data, cutter head angle data and feed rate data are collected in real time;

[0060] Inputting the cutter head speed data, cutter head angle data, cutter feed rate data and resistance data into an intelligent module;

[0061] The scraper wear amount, scraper integrity rate and scraper predicted life output by the intelligent module are received and displayed.

[0062] In a specific embodiment of the present invention, the detection method of the present invention further comprises:

[0063] In the early stage of shield tunneling construction, construction parameters within a set distance are selected as training data. The selected construction parameters include resistance data, cutter head speed data, cutter head angle data, and feed rate data.

[0064] Use construction parameters to calculate and obtain corresponding constraint results;

[0065] The training data and the corresponding constraint results are subjected to model training of the corresponding machine learning algorithm to obtain an intelligent module.

[0066] In a specific embodiment of the present invention, before the cutter disc speed data, cutter disc angle data, feed rate data and resistance data are input into an intelligent module, the cutter disc speed data, cutter disc angle data, feed rate data and resistance data are filtered and cleaned.

[0067] Further, the filtered and cleaned data is stored in a filtering database.

[0068] In a specific implementation of the present invention, the detection method of the present invention further comprises: storing the cutter disc rotation speed data, cutter disc angle data, cutter feed rate data and resistance data in a database.

[0069] The beneficial effects of the scraper status real-time detection system and method of the present invention include:

[0070] The resistance sensor collects the tool wear and transmits it to the data transmission module. The wired / wireless data transmission module combines the collected construction data and sends it to the data platform to back up the data and filter and clean it at the same time.

[0071] The processed data is transmitted to the intelligent module through the data platform for data mining. The machine learning intelligent algorithm is used to calculate the wear amount, intactness rate and other core indicators of the tool, and predict the working life. The data is transmitted back to the computing platform for visual display.

[0072] By studying the layout of hydraulic and electrical signal wear sensors, the accuracy of characterizing the overall wear of regional tools is improved.

[0073] The present invention is described in detail above in conjunction with the embodiments of the accompanying drawings. A person skilled in the art can make various variations of the present invention according to the above description. Therefore, certain details in the embodiments should not constitute a limitation of the present invention, and the scope of protection of the present invention shall be defined by the scope of the attached claims.

Claims

1. A real-time detection method for scraper status, characterized in that: The steps include: A resistance sensor is installed in the scraper, and the resistance data of the scraper during operation is detected in real time by the resistance sensor; During the shield tunneling process, the cutter head speed data, cutter head angle data and feed rate data are collected in real time; Inputting the cutter head speed data, cutter head angle data, cutter feed rate data and resistance data into an intelligent module; The scraper wear amount, scraper integrity rate and scraper predicted life output by the intelligent module are received and displayed.

2. The real-time detection method for scraper status according to claim 1, characterized in that: Also includes: In the early stage of shield tunneling construction, construction parameters within a set distance are selected as training data. The selected construction parameters include resistance data, cutter head speed data, cutter head angle data, and feed rate data. Calculating and obtaining corresponding constraint results using the construction parameters; The training data and the corresponding constraint results are subjected to model training of a corresponding machine learning algorithm to obtain an intelligent module.

3. The real-time detection method of scraper status according to claim 1, characterized in that: Before the cutter disc speed data, cutter disc angle data, cutter feed rate data and resistance data are input into an intelligent module, the cutter disc speed data, cutter disc angle data, cutter feed rate data and resistance data are filtered and cleaned.

4. The real-time detection method of scraper status according to claim 1, characterized in that: Also includes: The cutter head rotation speed data, cutter head angle data, cutter feed rate data and resistance data are stored in a database.

5. A real-time detection system for scraper status, characterized in that: include: The resistance sensor installed in the scraper is used to detect the resistance data in real time during the operation of the scraper; Construction data acquisition unit, used to collect data on cutter head speed, cutter head angle and feed rate in real time during shield tunneling; A data platform connected to the resistance sensor and the construction data acquisition unit, used to receive the resistance data detected by the resistance sensor in real time and the cutter head speed data, cutter head angle data and feed rate data collected by the construction data acquisition unit in real time; An intelligent module connected to the data platform, the intelligent module is used to receive the resistance data, the cutter head speed data, the cutter head angle data and the feed rate data sent by the data platform, and output the corresponding scraper wear amount, scraper integrity rate and scraper predicted life to the data platform; The display unit connected to the data platform is used to display the scraper wear amount, scraper integrity rate and scraper predicted life sent by the data platform.

6. The real-time scraper status detection system according to claim 5, characterized in that: The intelligent module is obtained by model training using a machine learning algorithm. The training data for the model training are construction parameters collected within a set distance in the early stage of shield tunneling construction. The construction parameters include resistance data, cutter head speed data, cutter head angle data, and feed rate data. The training data also includes constraint results calculated based on the construction parameters.

7. The real-time scraper status detection system according to claim 5, characterized in that: The data platform filters and cleans the resistance data, the cutter disc speed data, the cutter disc angle data and the feed rate data before sending the resistance data, the cutter disc speed data, the cutter disc angle data and the feed rate data to the intelligent module.

8. The real-time scraper status detection system according to claim 5, characterized in that: It also includes a database connected to the data platform, and the database is used to store the cutter disc speed data, cutter disc angle data, feed rate data and resistance data.

Images