Bolt state monitoring method, device and system

Abstract

The invention provides a bolt state monitoring method, device and system, and the method comprises the steps: S1, collecting a state parameter of a bolt in an initial state, and setting the state parameter as a bolt state 1; s2, collecting state parameters of the bolt according to a preset time interval, and setting the state parameters as a bolt state 2; s3, comparing the bolt state 2 with the bolt state 1, and calculating a bolt state variable quantity; s4, the bolt state variable quantity is compared with a bolt health evaluation value, if the bolt state variable quantity is lower than the bolt health evaluation value, it is determined that the bolt is in a healthy state at the time, and the steps S2 to S4 are repeated; and if the bolt state variation is higher than the bolt health evaluation value, determining that the bolt is in an abnormal state at the time, and outputting a manual processing early warning. By automatically collecting the state parameters of the bolt and comparing the state parameters with abnormal or healthy parameters in the database, the state of the bolt is automatically judged, so that an alarm is given, the manual maintenance cost is reduced, problems can be found more quickly, and losses are reduced.

Description

Technical Field

[0001] The present invention relates to the field of state monitoring of mechanical fastening devices, and particularly to a method, device and system for monitoring the state of bolts. Background Art

[0002] Wind energy is a clean energy source with relatively stable output, and large wind turbines are one of the best devices for converting wind energy. As long as the wind turbines are set high enough and the area is open, wind energy can be continuously converted into electrical energy for 24 hours. With the development of wind turbine technology, the energy conversion efficiency can be as high as 40% - 50%.

[0003] The tower barrels, yaw and rotating parts (such as hubs, main shafts, blades, etc.) of large wind turbines are connected by high-strength bolts. Due to the long-term influence of wind force, blade rotation, yaw and pitch change on the wind turbines, the bolts are under alternating loads of working conditions for a long time. Under complex mechanical environments, vibration and resonance effects, fastener failures such as loosening or fracture are likely to occur, which directly affects the overall stable operation of the wind turbine unit. In order to ensure the overall stable operation of the wind turbine, scientific and reasonable maintenance techniques need to be adopted, such as randomly inspecting 10% - 20%, annual torque application and irregular inspection, etc. For tens of thousands of bolts in the wind turbine, the maintenance cost is extremely high, and frequent torque application to the bolts will also damage the bolts at the same time.

[0004] In order to reduce the number of maintenance times, lower the maintenance cost and timely detect problems existing in the bolts, there is an urgent need for a method, device and system capable of monitoring the state of bolts. Summary of the Invention

[0005] In order to solve the technical problem of needing to repair the wind turbine without stopping and monitoring the state of bolts, The present invention provides a method for monitoring the state of bolts, which is characterized by including: S1: Collect the state parameters of the bolt and the nut matching the bolt in the initial state, and set it as bolt state 1; S2: Collect the state parameters of the bolt and the nut matching the bolt at a certain time interval, and set it as bolt state 2; S3: Compare bolt state 2 with bolt state 1, and calculate the bolt state change amount; S4: Compare the bolt state change amount with a preset value, If the bolt state change amount is lower than the predetermined value, it is determined that the bolt is in a healthy state at this time, and repeat the above steps S2 to S4; If the bolt state change amount is higher than the predetermined value, it is determined that the bolt is in an abnormal state at this time, output an alarm signal and notify manual handling; In a preferred embodiment of the present invention, the status parameters of the bolt and the nut matching the bolt are collected by a passive RFID tag. The passive RFID tag includes an RFID chip and a backplane. The RFID chip is connected to the backplane through conductive pins. The RFID tag is activated under a specific electromagnetic wave emitted by an external information transmitter and records the status parameters of the bolt and the nut matching the bolt.

[0006] In a preferred embodiment of the present invention, the status parameters of the bolt and the nut matching the bolt include the relative position angle of the bolt and the nut matching the bolt or the relative displacement distance of the bolt and the nut matching the bolt.

[0007] In a preferred embodiment of the present invention, the relative position angle of the bolt and the nut matching the bolt is obtained by a bolt loosening monitoring sensor.

[0008] In a preferred embodiment of the present invention, the relative displacement distance of the bolt and the nut matching the bolt is obtained by a bolt fracture monitoring sensor.

[0009] In a preferred embodiment of the present invention, the status parameters of the bolt in the abnormal state after being manually processed are set as the initial status parameters.

[0010] In a preferred embodiment of the present invention, the abnormal state of the bolt is divided into immediate maintenance and pending maintenance, and a maintenance plan is formulated. The immediate maintenance includes arranging manual processing immediately when one bolt is abnormal; the pending maintenance includes waiting for multiple bolts to be abnormal and then arranging manual processing.

[0011] In a preferred embodiment of the present invention, in S3, the certain time interval for collecting the status parameters of the bolt and the nut matching the bolt is adjustable. The time interval includes 1 second, 10 seconds, 1 minute, 60 minutes, 3 hours, 24 hours, 240 hours or 180 days.

[0012] A bolt status monitoring device for performing the bolt status monitoring method according to any one of claims 1 to 8, the bolt status monitoring device comprising: A bolt status parameter collection and transmission module configured to be activated under a specific electromagnetic wave emitted by an external information collector, collect the status parameters of the bolt and the matching nut, generate a digital signal, and transmit the digital signal; An early warning module configured to issue an early warning for manual processing after the bolt health model outputs an abnormal state; A storage module configured to store the status parameters, the manual processing early warning, and the bolt health model.

[0013] A bolt status monitoring system for operating the bolt status monitoring device described in claim 9, the bolt status monitoring system comprising: a status monitoring device, an information collector, and a server; The status monitoring device is used to monitor the status parameters of the bolt and the nut matching the bolt; The information collector is used to emit a specific electromagnetic wave to activate the status monitoring equipment, collect and transmit the status parameters; The server is used to store the bolt status parameters.

[0014] Compared with the prior art, the beneficial effects of the present invention are as follows: By automatically collecting the status parameters of the bolt and comparing them with the abnormal or healthy parameters in the database, the status of the bolt is automatically judged, and thus an alarm is given, reducing the manual maintenance cost, being able to detect problems faster, and reducing losses.

[0015] Other features and advantages of the present invention will be described in the following description, and part of them will be obvious from the description, or understood by implementing the technical solutions of the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures and / or processes specifically pointed out in the description, claims, and drawings. Description of the Drawings

[0016] Figure 1 It is a step flow chart of the bolt status monitoring method of the present invention; Figure 2 It is a flow chart for establishing the bolt health model of the present invention; Figure 3 It is a structural schematic diagram of a bolt status monitoring device of the present invention; Figure 4 It is a structural schematic diagram of the bolt status monitoring system of the present invention. Detailed Embodiments

[0017] The following will combine the drawings and embodiments to elaborate in detail on the implementation manners of the present invention, so as to fully understand how the present invention uses technical means to solve technical problems and achieve the realization process of technical effects and implement accordingly. It should be noted that these specific descriptions are only to make those of ordinary skill in the art more easily and clearly understand the present invention, rather than a limiting interpretation of the present invention; for example, the first and second mentioned in the embodiments of the present invention do not constitute a limitation, but are only used to represent the serial numbers of multiple identical or similar devices or mechanisms. Those of ordinary skill in the art can also readjust these serial numbers during the process of expressing conveniently or sorting out technical solutions; moreover, in different embodiments, alternative solutions are described for some mechanisms, and these alternatives can also be applied to other identical or similar devices or mechanisms; and as long as there is no conflict, the various embodiments in the present invention and the various features in each embodiment can be combined with each other, and the formed technical solutions are all within the protection scope of the present invention.

[0018] The technical solutions of the present invention will be described in detail below with reference to the drawings and specific embodiments:

[0019] As Figure 1 shown, the present invention provides a method for monitoring the state of bolts, including: S1: Obtain the state parameters of the bolt and the nut matching the bolt in the initial state, and set it as bolt state 1; Through the bolt state monitoring device sleeved on the bolt and the nut matching the bolt, obtain the state information of the bolt and the nut matching the bolt. In this embodiment, the bolt state monitoring device uses an RFID passive tag to record and transmit the states of the bolt and the nut. The passive RFID tag will be activated after receiving specific electromagnetic waves from the outside, so as to record the state of the monitoring sensor at that time. The obtained state parameters of the bolt and the nut include the relative position angle of the bolt and the nut matching the bolt or the relative displacement distance of the bolt and the nut matching the bolt. The relative displacement distance reflects whether the bolt and the nut are broken, and the relative position angle reflects the degree of looseness of the bolt and the nut. The relative displacement distance is obtained by the bolt fracture monitoring sensor, and the relative position angle is obtained by the bolt loosening monitoring sensor.

[0020] S2: Collect the state parameters of the bolt and the nut matching the bolt at preset time intervals, and set it as bolt state 2; Over time, the bolt and nut may become loose horizontally or break vertically. Therefore, it is necessary to monitor the state parameters of the bolt and nut at regular intervals, and this preset time interval can be adjusted according to different actual situations and monitoring devices. In an alternative embodiment, the preset time intervals include 1 second, 10 seconds, 1 minute, 60 minutes, 3 hours, 24 hours, 240 hours, or 180 days. In this embodiment, in order to monitor the bolt and nut more accurately, the time interval for the external signal generator to emit specific electromagnetic waves is very short, and the preset time interval is 1 second.

[0021] S3: Compare the bolt state 2 with the bolt state 1 and calculate the bolt state change amount; The bolt state change amount is the parameter change of the bolt and nut within this preset time interval.

[0022] S4: Compare the bolt state change amount with the bolt health evaluation value. If the bolt state change amount is lower than the bolt health evaluation value, it is determined that the bolt is in a healthy state at this time, and repeat the above steps S2 to S4; If the bolt state change amount is higher than the bolt health evaluation value, it is determined that the bolt is in an abnormal state at this time, output an alarm signal and notify for manual handling; As Figure 2 shown, the bolt health evaluation value is obtained from the bolt health model, and the bolt health model is trained using a big data model based on the state parameters of many bolts of the same model and manually adjusted parameters in the initial state. The big data model includes a neural network model. In this embodiment, the neural network model selects a recurrent neural network. The main purpose of the recurrent neural network is to process and predict sequence data. In a fully connected neural network or a convolutional neural network, the network structure goes from the input layer to the hidden layer and then to the output layer, and the layers are fully connected or partially connected, but the nodes between each layer are not connected. The recurrent neural network is designed to depict the relationship between the current output of a sequence and the previous information. In terms of the network structure, the recurrent neural network will remember the previous information and use the previous information to affect the subsequent output. That is to say, the nodes between the hidden layers of the recurrent neural network are connected. The input of the hidden layer includes not only the output of the input layer but also the output of the hidden layer at the previous moment. In the present invention, the bolt health evaluation value is not only affected by the initial state parameters of the bolt but also by the repair state of manual maintenance. Over time, in the iteration of the recurrent neural network, using this bolt health evaluation value to judge the health state of this type of bolt and its matching nut will become more and more accurate.

[0023] The recurrent neural network of the bolt health model includes an input layer, a hidden layer, and an output layer, and the mathematical expression of the hidden layer neurons is as follows.

[0024] S(t) = f[wx·x(t) + ws·x(t - 1)] + M Where: S(t) is the value of the neuron in the hidden layer at time t; f(x) is the activation function; w is the weight; x(t) is the time series value at the input end at time t, and M is the manually adjusted parameter.

[0025] For the output layer, it satisfies the following mathematical expression.

[0026] y(t) = g[wy·S(t)] Where: y(t) is the result of the output layer at time t; g(x) is the activation function; w is the weight. [[ID=eleven]]

[0027] As Figure 3 shown, the embodiment of the present invention is also equipped with a bolt status monitoring device for implementing the bolt status monitoring method according to any one of claims 1 to 8. The bolt status monitoring device includes: The bolt status parameter collection and transmission module 11 is configured to be activated under a specific electromagnetic wave emitted by an external information collector, collect the status parameters of the bolt and the matching nut, generate a digital signal, and transmit the digital signal; The early warning module 12 is configured to issue an artificial processing early warning after the bolt health model outputs an abnormal state; The storage module 13 is configured to store the status parameters, artificial processing early warnings, and bolt health models. [[ID=2eleven]]

[0028] As Figure 4 shown, the embodiment of the present invention is also equipped with a bolt status monitoring system for operating the bolt status monitoring device of claim 9. The bolt status monitoring system includes: a status monitoring device, an information collector, and a server; The status monitoring device 21 is used to monitor and collect the status parameters of the bolt and the nut matching the bolt; The information collector 22 is used to emit a specific electromagnetic wave to activate the status monitoring equipment and collect and transmit the status parameters; The server 23 is used to store the bolt status parameters and bolt health evaluation values.

[0029] Other features and advantages of the present invention will be described in the subsequent description, and part of them will be obvious from the description, or understood by implementing the technical solutions of the present invention. The objectives and other advantages of the present invention can be achieved and obtained through the structures and / or processes specifically pointed out in the description, claims, and drawings.

[0030] Finally, it should be noted that the above description is only the best embodiment of the present invention and does not impose any formal limitations on the present invention. Any person skilled in the art can make many possible changes and simple substitutions to the technical solution of the present invention by using the disclosed methods and technical contents within the scope of the technical solution of the present invention. All of these fall within the scope of protection of the technical solution of the present invention.

Claims

1. A bolt condition monitoring method, characterized in that, It includes the following steps: S1: Obtain the state parameters of the bolt and the nut matching the bolt in the initial state, and set them as bolt state 1; S2: Obtain the state parameters of the bolt and the nut matching the bolt at preset time intervals, and set them as bolt state 2; S3: Compare the bolt state 2 with the bolt state 1, and calculate the bolt state change amount; S4: Compare the bolt state change amount with the bolt health evaluation value, If the bolt state change amount is lower than the bolt health evaluation value, it is determined that the bolt is in a healthy state at this time, and repeat the above steps S2 to S4; If the bolt state change amount is higher than the bolt health evaluation value, it is determined that the bolt is in an abnormal state at this time, and output an alarm signal or a manual processing warning.

2. The bolt state monitoring method according to claim 1, wherein, The state parameters of the bolt and the nut matching the bolt are obtained through a passive RFID tag. The passive RFID tag includes an RFID chip and a backplane. The RFID chip is connected to the backplane through conductive pins. The RFID tag is activated under the specific electromagnetic wave emitted by an external information transmitter and records the state parameters of the bolt and the nut matching the bolt.

3. A method for monitoring the state of a bolt according to claim 1, characterized in that, The state parameters of the bolt and the nut matching the bolt include the relative position angle of the bolt and the nut matching the bolt or the relative displacement distance of the bolt and the nut matching the bolt.

4. A method for monitoring the state of a bolt according to claim 3, characterized in that, The relative position angle of the bolt and the nut matching the bolt is obtained through a bolt loosening monitoring sensor.

5. A bolt status monitoring method according to claim 3, characterized in that, The relative displacement distance of the bolt and the nut matching the bolt is obtained through a bolt fracture monitoring sensor.

6. The method for monitoring the state of a bolt according to claim 1, wherein In step S4, the bolt health evaluation value is obtained from a bolt health model. The bolt health model is trained by using a big data model based on the bolt state parameters and manual adjustment parameters in the initial state. The big data model includes a neural network model.

7. A method for monitoring the state of a bolt according to claim 1, characterized in that, The bolt abnormal state is divided into immediate repair and pending repair, and a repair plan is formulated. The immediate repair includes arranging manual processing immediately when one bolt is abnormal; the pending repair includes waiting for multiple bolts to be abnormal and then arranging manual processing.

8. A method for monitoring the state of a bolt according to claim 1, characterized in that, In S2, the preset time interval for obtaining the state parameters of the bolt and the nut matching the bolt is adjustable. The time interval includes 1 second, 10 seconds, 1 minute, 60 minutes, 3 hours, 24 hours, 240 hours or 180 days.

9. A bolt status monitoring device for implementing the bolt status monitoring method according to any one of claims 1 to 8, characterized in that, The bolt state monitoring device includes: A bolt state parameter acquisition and transmission module, configured to be activated under the specific electromagnetic wave emitted by an external information collector, collect the state parameters of the bolt and the matching nut, generate a digital signal, and transmit the digital signal; A warning module, configured to issue a manual processing warning after the bolt state is an abnormal state; A storage module, configured to store the state parameters, the manual processing warning or the bolt health evaluation value.

10. A bolt condition monitoring system for operating the bolt condition monitoring device according to claim 9, characterized in that, The bolt state monitoring system includes: a state monitoring device, an information collector and a server; The state monitoring device is used to monitor the state parameters of the bolt and the nut matching the bolt; The information collector is used to emit specific electromagnetic waves to activate the status monitoring equipment, and collect and transmit the status parameters; The server is used to store the bolt status parameters, the bolt health evaluation value or the manual processing warning.

Images