Cable tensioning fault pre-judgment method, device and system and storage medium
Through the convolutional neural network and long-term memory network model combined with the cable state equation, cable tension failure is predicted, and the problem of inefficient detection of cable tension failures in the existing technology is solved, and early warning of cable failures and mechanical equipment operation is achieved. Improved efficiency.
Patent Information
- Application Number
- CN202411324676.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-23
- Publication Date
- 2024-12-06
AI Technical Summary
The existing technology cannot effectively predict cable tension failures, resulting in too tight or too loose cables during operation of mechanical equipment, which may lead to wear, breakage or safety hazards. The existing fault detection relies on manual inspection, which is inefficient and poor real-time.
Using a long and short-term memory network model based on convolutional neural network combined with pre-constructed cable state equations, the cable state is predicted by obtaining cable image data and mechanical equipment position data, and the tension fault prediction is carried out to achieve early warning of cable faults. .
It realizes early warning of cable failures, avoids cable failures, reduces manual inspection costs and maintenance costs, and improves the operating economic benefits of mechanical equipment.
Smart Images

Figure CN119085556A_ABST
Abstract
Description
Technical Field
[0001] The invention relates to a cable tension fault prediction method, device, system and storage medium, belonging to the technical field of cable fault detection. Background Art
[0002] Cables are used as a bridge between large mechanical equipment such as port ship unloaders, ship loaders, bucket wheel excavators and ground connection boxes and control systems, and are responsible for transmitting power and signals. The state of the cable directly affects the normal operation and operating efficiency of the mechanical equipment, and is crucial to the safe operation of the mechanical equipment. The cable is generally connected to the ground connection box through a slip ring box, cable reel, and cable guide.
[0003] When the cable is too tight, it will be in a tight state for a long time, which will increase the friction between the cable and components such as the reel and slip ring, causing the cable sheath to wear faster and may even wear the internal metal core. A cable that is too tight will be subjected to greater tension, which can easily cause the cable to stretch and deform, or even break, resulting in power or signal interruption.
[0004] When the cable is too loose, it is easy for the loose cable to get entangled, dragged or fall during the movement of mechanical equipment, which may trip the operator or get stuck in other parts of the equipment, causing safety hazards or cable breakage.
[0005] When the mechanical equipment moves quickly or starts and stops frequently, the cable may become tight due to inertia. The cable reel motor speed is set too fast, causing the cable to be too tight when the reel is retracted and released to keep up with the moving speed of the mechanical equipment. The cable may also be too tight when the cable is pulled by external force and the cable reel is retracted.
[0006] When the cable reel's motor fails or the control fails, causing the cable to be unable to be retracted or released normally, the cable will be too loose; when the hysteresis coupling between the cable reel's star-shaped differential gear and the motor is damaged, causing the cable to be unable to be retracted or released normally, the cable will be too loose.
[0007] For cable fault detection, existing technologies mainly rely on manual inspections and regular checks, which are highly subjective and inefficient. The cable tension is judged by the limit position of the guide rods on both sides of the cable and in the middle. On the one hand, during the start and stop of mechanical equipment, the cable will be instantly tensioned, which is easy to cause false alarms; on the other hand, the real-time performance is poor and the tension trend cannot be judged. The relevant problems can only be found after the cable is damaged. Summary of the invention
[0008] The object of the present invention is to provide a cable tension fault prediction method, device, system and storage medium, which can predict cable faults.
[0009] In order to achieve the above object, the present invention provides the following technical solutions: In a first aspect, the present invention provides a cable tension fault prediction method, wherein the cable is connected between a ground junction box and a mechanical device via a cable reel, and the cable reel retracts and releases the cable as the mechanical device reciprocates, and the method comprises: Obtain image data of cables and location data of mechanical equipment; Input the cable image data into the trained long short-term memory network model based on convolutional neural network to obtain the cable status prediction value; Based on the position data of the mechanical equipment and the pre-built cable state equation, the cable state prior value is calculated; Based on the cable state prediction value and the cable state prior value, the cable tension fault is predicted and the cable tension fault prediction result is obtained; Among them, the long short-term memory network model based on convolutional neural network is trained based on pre-acquired cable image data, and the cable state equation is constructed based on pre-acquired mechanical equipment position data and its corresponding cable state measured value.
[0010] In combination with the first aspect, further, the position data of the mechanical equipment includes a horizontal distance from the mechanical equipment to a center point of the cable reel.
[0011] In combination with the first aspect, further, the cable state includes an angle between the cable and a horizontal plane and a horizontal distance from a contact point between the cable and the horizontal plane to a center point of the cable reel; The cable state prediction value includes a prediction value of the angle between the cable and the horizontal plane and a prediction value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel; The cable state prior value includes a prior value of the angle between the cable and the horizontal plane and a prior value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel; The measured values of the cable status include the measured value of the angle between the cable and the horizontal plane and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel.
[0012] In combination with the first aspect, further, based on the cable state prediction value and the cable state prior value, the cable tension fault is predicted, and obtaining the cable tension fault prediction result includes: If the predicted value of the angle between the cable and the horizontal plane is less than the prior value of the angle between the cable and the horizontal plane, and the difference between the predicted value of the angle between the cable and the horizontal plane and the prior value of the angle between the cable and the horizontal plane is greater than a first preset threshold, or the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel, and the difference between the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel and the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than a second preset threshold, it is predicted that the cable is over-tightened; If the predicted value of the angle between the cable and the horizontal plane is greater than the prior value of the angle between the cable and the horizontal plane, and the difference between the predicted value of the angle between the cable and the horizontal plane and the prior value of the angle between the cable and the horizontal plane is greater than the third preset threshold, or the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is less than the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel, and the difference between the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel and the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than the fourth preset threshold, it is predicted that the cable is too loose.
[0013] In combination with the first aspect, further, the long short-term memory network model based on the convolutional neural network includes: Input layer, used to input cable image data; The convolutional neural network layer is used to extract features from the cable image data and obtain the cable status feature map; Long short-term memory network layer, used to capture the temporal relationship between cable state feature graphs; The output layer is used to output the cable status prediction value according to the temporal relationship between the cable status feature graphs.
[0014] In combination with the first aspect, further, obtaining the position data of the mechanical equipment and the corresponding measured value of the cable status includes: Setting position sequence points on the reciprocating track of the mechanical equipment; When there is no cable fault, collect the horizontal distance from the mechanical equipment to the center point of the cable reel, the measured value of the angle between the cable and the horizontal plane, and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel when the mechanical equipment is at each position sequence point.
[0015] In combination with the first aspect, further, constructing a cable state equation based on pre-acquired position data of mechanical equipment and its corresponding measured cable state value includes: Based on the horizontal distance from the mechanical equipment to the center point of the cable reel and the corresponding measured value of the angle between the cable and the horizontal plane, discrete angle data points are drawn in a rectangular coordinate system; Based on the horizontal distance from the mechanical equipment to the center point of the cable reel and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel, discrete horizontal distance data points are drawn in a rectangular coordinate system; Fitting the angle data points and the horizontal distance data points respectively to obtain the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment, and the functional relationship between the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment; The cable state equation is composed of the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment, and the functional relationship between the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment.
[0016] In a second aspect, the present invention provides a cable tension fault prediction device, comprising: A data acquisition module, used to acquire image data of cables and position data of mechanical equipment; A state prediction module is used to input the image data of the cable into a trained long short-term memory network model based on a convolutional neural network to obtain a predicted value of the cable state; A state calculation module is used to calculate a priori values of cable states based on position data of mechanical equipment and a pre-built cable state equation; A tension fault prediction module is used to predict the cable tension fault based on the cable state prediction value and the cable state prior value, and obtain the cable tension fault prediction result; Among them, the long short-term memory network model based on convolutional neural network is trained based on pre-acquired cable image data, and the cable state equation is constructed based on pre-acquired mechanical equipment position data and its corresponding cable state measured value.
[0017] In a third aspect, the present invention provides a computer system, comprising: Storage medium: used to store computer programs; Processor: used to execute the computer program to implement the steps of the cable tensioning fault prediction method described in any one of the first aspects.
[0018] In a fourth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the cable tensioning fault prediction method described in any one of the first aspects.
[0019] Fifthly, the present invention provides a computer program product, comprising a computer program, which, when executed by a processor, implements the steps of the cable tensioning fault prediction method described in any one of the first aspects.
[0020] Compared with the prior art, the present invention has the following beneficial effects: The cable tension fault prediction method provided by the present invention constructs a cable state equation based on pre-acquired position data of mechanical equipment and its corresponding actual cable state value, calculates a cable state priori value, inputs the cable image data into a trained long short-term memory network model based on a convolutional neural network, obtains a cable state prediction value, and performs cable tension fault prediction based on the cable state prediction value and the cable state priori value. The cable tension fault prediction result can be obtained, and early warning of cable faults can be achieved, which can not only effectively avoid the occurrence of cable faults, but also reduce manual inspection costs and maintenance and repair costs, and improve the operating economic benefits of mechanical equipment. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] Figure 1 is a flow chart of a cable tension fault prediction method provided by an embodiment of the present invention; Figure 2 It is a schematic diagram of connecting a cable provided by an embodiment of the present invention to a mechanical device via a cable reel. DETAILED DESCRIPTION
[0022] The technical solution of the present application is further described in detail below in conjunction with specific implementation methods.
[0023] The embodiments of the present application are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements with the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and should not be construed as limitations on the present application. In the absence of conflict, the embodiments of the present application and the technical features in the embodiments may be combined with each other.
[0024] Embodiment 1: Figure 1 This is a flow chart of a cable tension fault prediction method provided by this embodiment. This flow chart only shows the logical sequence of the method of this embodiment. Different methods can be used without conflict. Figure 1 The steps shown or described are accomplished in the order shown.
[0025] The cable tension fault prediction method provided in this embodiment can be applied to a terminal and can be executed by a cable tension fault prediction device, which can be implemented by software and / or hardware. The device can be integrated in a terminal, for example: any tablet computer or computer device with communication function.
[0026] In this embodiment, Figure 2 As shown, the cable is connected between the ground junction box and the mechanical equipment through a cable reel, and the cable reel retracts and releases the cable as the mechanical equipment reciprocates.
[0027] See also Figure 1 The cable tension fault prediction method of this embodiment specifically includes the following steps: Step 1: Obtain image data of the cable and location data of the mechanical equipment; In this embodiment, the image data of the cable is collected in real time at different positions by a monitoring device installed on the mechanical equipment along with the reciprocating motion of the mechanical equipment, and the image data of the cable includes the time sequence state of the cable. The position data of the mechanical equipment is obtained in real time by a position sensor installed on the mechanical equipment, and the position data of the mechanical equipment includes the horizontal distance from the mechanical equipment to the center point of the cable reel.
[0028] Step 2: Input the cable image data into the trained long short-term memory network model based on convolutional neural network to obtain the cable status prediction value; In this embodiment, the long short-term memory network model based on the convolutional neural network is trained based on the pre-acquired cable image data.
[0029] The long short-term memory network model based on convolutional neural network specifically includes: Input layer, used to input cable image data; The convolutional neural network layer is used to extract features from the cable image data and obtain the cable status feature map; Long short-term memory network layer, used to capture the temporal relationship between cable state feature graphs; The output layer is used to output the cable status prediction value according to the temporal relationship between the cable status feature graphs.
[0030] The pre-acquired cable image data is input into a long short-term memory network model based on a convolutional neural network for training, and a trained long short-term memory network model based on a convolutional neural network is obtained.
[0031] The cable image data is input into the trained long short-term memory network model based on convolutional neural network to obtain the cable status prediction value.
[0032] In this embodiment, the cable state includes the angle between the cable and the horizontal plane and the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel.
[0033] The cable status prediction value includes the predicted value of the angle between the cable and the horizontal plane and the predicted value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel.
[0034] The cable status prediction value indicates the cable status at the next moment predicted by the long short-term memory network model based on the convolutional neural network according to the image data of the cable at the current moment, that is, the angle between the cable and the horizontal plane at the next moment, and the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel at the next moment.
[0035] Step 3: Based on the position data of the mechanical equipment and the pre-built cable state equation, calculate the cable state prior value; In this embodiment, the cable state equation is constructed based on the pre-acquired position data of the mechanical equipment and the corresponding actual measured values of the cable state.
[0036] The measured values of the cable status include the measured value of the angle between the cable and the horizontal plane and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel.
[0037] Obtaining the location data of the mechanical equipment and the corresponding measured value of the cable status specifically includes the following steps: Step 1: Set position sequence points on the reciprocating track of the mechanical equipment; Step 2: When there is no cable fault, collect the horizontal distance from the mechanical equipment to the center point of the cable reel, the measured value of the angle between the cable and the horizontal plane, and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel when the mechanical equipment is at each position sequence point.
[0038] In this embodiment, the measured value of the cable status represents the angle between the cable and the horizontal plane, and the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel when the mechanical equipment is at each position sequence point when the cable is fault-free. The measured value of the cable status represents the real state of the cable when there is no fault, that is, the normal state.
[0039] The cable state equation is constructed based on the pre-acquired position data of the mechanical equipment and the corresponding measured value of the cable state, which specifically includes the following steps: Step 1: Based on the horizontal distance from the mechanical equipment to the center point of the cable reel and the corresponding measured value of the angle between the cable and the horizontal plane, draw discrete angle data points in the rectangular coordinate system; In this embodiment, in a rectangular coordinate system, the horizontal distance from the mechanical equipment to the center point of the cable reel when the mechanical equipment is at each position sequence point is used as the horizontal coordinate, and the measured value of the angle between the cable and the horizontal plane is used as the vertical coordinate. Discrete angle data points are drawn, and each angle data point corresponds to a position sequence point.
[0040] Step 2: Based on the horizontal distance from the mechanical equipment to the center point of the cable reel and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel, draw discrete horizontal distance data points in a rectangular coordinate system; In this embodiment, in a rectangular coordinate system, the horizontal distance from the mechanical equipment to the center point of the cable reel when the mechanical equipment is at each position sequence point is used as the horizontal coordinate, and the measured value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is used as the vertical coordinate. Discrete horizontal distance data points are drawn, and each horizontal distance data point corresponds to a position sequence point.
[0041] Step 3: Fit the angle data points and the horizontal distance data points respectively to obtain the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment, and the functional relationship between the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment; In this embodiment, each discrete angle data point is fitted to obtain the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment; each discrete horizontal distance data point is fitted to obtain the functional relationship between the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment.
[0042] Step 4: The cable state equation is composed of the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment, and the functional relationship between the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment.
[0043] In this embodiment, it is assumed that the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment is: , the functional relationship between the horizontal distance from the point where the cable contacts the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment is: , then the cable state equation is: ; in, Indicates the angle between the cable and the horizontal plane. Indicates the horizontal distance from the point where the cable contacts the horizontal plane to the center of the cable reel. Indicates the position data of the mechanical equipment, that is, the horizontal distance from the mechanical equipment to the center point of the cable reel. A function representing the angle between the cable and the horizontal plane with respect to the position data of the mechanical equipment, It represents the function of the horizontal distance from the point where the cable contacts the horizontal plane to the center point of the cable drum with respect to the position data of the mechanical equipment.
[0044] In this embodiment, the position data of the mechanical equipment, that is, the horizontal distance from the mechanical equipment to the center point of the cable reel, is substituted into the pre-constructed cable state equation to calculate the cable state prior value.
[0045] The cable state prior value includes the angle prior value between the cable and the horizontal plane and the horizontal distance prior value from the contact point between the cable and the horizontal plane to the center point of the cable reel.
[0046] The cable status prior value indicates the angle between the cable and the horizontal plane, and the horizontal distance from the point where the cable contacts the horizontal plane to the center of the cable reel when the mechanical equipment is in various positions when the cable is fault-free. The cable status prior value represents the actual state of the cable when there is no fault, that is, the normal state.
[0047] Step 4: Based on the cable state prediction value and the cable state prior value, the cable tension fault is predicted to obtain the cable tension fault prediction result.
[0048] In this embodiment, based on the cable state prediction value and the cable state prior value, the cable tension fault is predicted, and obtaining the cable tension fault prediction result specifically includes: R1: If the predicted value of the angle between the cable and the horizontal plane is less than the prior value of the angle between the cable and the horizontal plane, and the difference between the predicted value of the angle between the cable and the horizontal plane and the prior value of the angle between the cable and the horizontal plane is greater than a first preset threshold, or the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel, and the difference between the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel and the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than a second preset threshold, it is predicted that the cable is over-tightened; R2: If the predicted value of the angle between the cable and the horizontal plane is greater than the prior value of the angle between the cable and the horizontal plane, and the difference between the predicted value of the angle between the cable and the horizontal plane and the prior value of the angle between the cable and the horizontal plane is greater than the third preset threshold, or the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is less than the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel, and the difference between the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel and the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than the fourth preset threshold, it is predicted that the cable is too loose.
[0049] The cable tension fault prediction method provided in the present embodiment constructs a cable state equation based on the pre-acquired position data of the mechanical equipment and the corresponding actual cable state value, calculates the cable state prior value, inputs the cable image data into the trained long short-term memory network model based on the convolutional neural network, obtains the cable state prediction value, and predicts the cable tension fault based on the cable state prediction value and the cable state prior value. The cable tension fault prediction result can be obtained, and the early warning of the cable fault can be realized, which can not only effectively avoid the occurrence of cable faults, but also reduce the manual inspection cost and maintenance and repair costs, and improve the economic benefits of the operation of mechanical equipment.
[0050] Embodiment 2: This embodiment provides a cable tension fault prediction device, comprising: A data acquisition module, used to acquire image data of cables and position data of mechanical equipment; A state prediction module is used to input the image data of the cable into a trained long short-term memory network model based on a convolutional neural network to obtain a predicted value of the cable state; A state calculation module is used to calculate a priori values of cable states based on position data of mechanical equipment and a pre-built cable state equation; A tension fault prediction module is used to predict the cable tension fault based on the cable state prediction value and the cable state prior value, and obtain the cable tension fault prediction result; Among them, the long short-term memory network model based on convolutional neural network is trained based on the pre-acquired cable image data, and the cable state equation is constructed based on the pre-acquired mechanical equipment position data and its corresponding cable state measured value.
[0051] The cable tension fault prediction device provided in the embodiment of the present application can execute the cable tension fault prediction method provided in Example 1 of the present application, and has the corresponding functional modules and beneficial effects of the execution method.
[0052] Embodiment 3: This embodiment provides a computer system, including: Storage medium: used to store computer programs; Processor: used to execute a computer program to implement the steps of the cable tension fault prediction method in Example 1.
[0053] Embodiment 4: This embodiment provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the cable tension fault prediction method in Embodiment 1 are implemented.
[0054] Embodiment 5: This embodiment provides a computer program product, including a computer program, which implements the steps of the cable tension fault prediction method in Embodiment 1 when executed by a processor.
[0055] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.
[0056] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0057] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0058] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0059] The above are only preferred implementations of the present application. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the technical principles of the present application. These improvements and modifications should also be regarded as the scope of protection of the present application.
Claims
1. A cable tension fault prediction method, wherein the cable is connected between the ground junction box and the mechanical equipment through a cable reel, and the cable reel retracts and releases the cable with the reciprocating motion of the mechanical equipment, characterized in that: The method comprises: Obtain image data of cables and location data of mechanical equipment; Input the cable image data into the trained long short-term memory network model based on convolutional neural network to obtain the cable status prediction value; Based on the position data of the mechanical equipment and the pre-built cable state equation, the cable state prior value is calculated; Based on the cable state prediction value and the cable state prior value, the cable tension fault is predicted and the cable tension fault prediction result is obtained; Among them, the long short-term memory network model based on convolutional neural network is trained based on pre-acquired cable image data, and the cable state equation is constructed based on pre-acquired mechanical equipment position data and its corresponding cable state measured value.
2. The cable tension fault prediction method according to claim 1, characterized in that: The position data of the mechanical equipment includes the horizontal distance from the mechanical equipment to the center point of the cable reel.
3. The cable tension fault prediction method according to claim 1, characterized in that: The cable status includes the angle between the cable and the horizontal plane and the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel; The cable state prediction value includes a prediction value of the angle between the cable and the horizontal plane and a prediction value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel; The cable state prior value includes a prior value of the angle between the cable and the horizontal plane and a prior value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel; The measured values of the cable status include the measured value of the angle between the cable and the horizontal plane and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel.
4. The cable tension fault prediction method according to claim 3, characterized in that: Based on the cable state prediction value and the cable state prior value, the cable tension fault is predicted, and the cable tension fault prediction result is obtained, including: If the predicted value of the angle between the cable and the horizontal plane is less than the prior value of the angle between the cable and the horizontal plane, and the difference between the predicted value of the angle between the cable and the horizontal plane and the prior value of the angle between the cable and the horizontal plane is greater than a first preset threshold, or the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel, and the difference between the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel and the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than a second preset threshold, it is predicted that the cable is over-tightened; If the predicted value of the angle between the cable and the horizontal plane is greater than the prior value of the angle between the cable and the horizontal plane, and the difference between the predicted value of the angle between the cable and the horizontal plane and the prior value of the angle between the cable and the horizontal plane is greater than the third preset threshold, or the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is less than the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel, and the difference between the predicted value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel and the prior value of the horizontal distance from the contact point of the cable with the horizontal plane to the center point of the cable reel is greater than the fourth preset threshold, it is predicted that the cable is too loose.
5. The cable tension fault prediction method according to claim 1, characterized in that: The long short-term memory network model based on convolutional neural network includes: Input layer, used to input cable image data; The convolutional neural network layer is used to extract features from the cable image data and obtain the cable status feature map; Long short-term memory network layer, used to capture the temporal relationship between cable state feature graphs; The output layer is used to output the cable status prediction value according to the temporal relationship between the cable status feature graphs.
6. The cable tension fault prediction method according to claim 1, characterized in that: Obtaining the location data of mechanical equipment and its corresponding measured values of cable status includes: Setting position sequence points on the reciprocating track of the mechanical equipment; When there is no cable fault, collect the horizontal distance from the mechanical equipment to the center point of the cable reel, the measured value of the angle between the cable and the horizontal plane, and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel when the mechanical equipment is at each position sequence point.
7. The cable tension fault prediction method according to claim 6, characterized in that: The cable state equation is constructed based on the pre-acquired position data of the mechanical equipment and the corresponding measured value of the cable state, including: Based on the horizontal distance from the mechanical equipment to the center point of the cable reel and the corresponding measured value of the angle between the cable and the horizontal plane, discrete angle data points are drawn in a rectangular coordinate system; Based on the horizontal distance from the mechanical equipment to the center point of the cable reel and the measured value of the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel, discrete horizontal distance data points are drawn in a rectangular coordinate system; Fitting the angle data points and the horizontal distance data points respectively to obtain the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment, and the functional relationship between the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment; The cable state equation is composed of the functional relationship between the angle between the cable and the horizontal plane and the position data of the mechanical equipment, and the functional relationship between the horizontal distance from the contact point between the cable and the horizontal plane to the center point of the cable reel and the position data of the mechanical equipment.
8. A cable tension fault prediction device, characterized in that: include: A data acquisition module, used to acquire image data of cables and position data of mechanical equipment; A state prediction module is used to input the image data of the cable into a trained long short-term memory network model based on a convolutional neural network to obtain a predicted value of the cable state; A state calculation module is used to calculate a priori values of cable states based on position data of mechanical equipment and a pre-built cable state equation; A tension fault prediction module is used to predict the cable tension fault based on the cable state prediction value and the cable state prior value, and obtain the cable tension fault prediction result; Among them, the long short-term memory network model based on convolutional neural network is trained based on pre-acquired cable image data, and the cable state equation is constructed based on pre-acquired mechanical equipment position data and its corresponding cable state measured value.
9. A computer system, characterized in that: include: Storage medium: used to store computer programs; Processor: used to execute the computer program to implement the steps of the cable tensioning fault prediction method according to any one of claims 1 to 7.
10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the cable tensioning fault prediction method according to any one of claims 1 to 7 are implemented.
