A current detection-based roller failure identification method

Abstract

The present application belongs to the technical field of safety monitoring of rolling machine, and specifically discloses a rolling machine fault identification method based on current detection, which comprises: obtaining the real-time current signal of the sawtooth cylinder in the rolling machine, inputting the real-time current signal into the working condition identification model, establishing the current current change curve, and determining the current working condition of the rolling machine according to the current current change curve; if the rolling machine is in the cotton jam state, inputting the image of the current change curve into the preset convolutional neural network, determining the cotton jam position, matching the real-time current signal with the preset early warning threshold corresponding to the cotton jam position, determining the cotton jam degree grade, determining the corresponding fault early warning operation from the preset early warning strategy according to the cotton jam fault state, and performing early warning according to the fault early warning operation. The present application improves the practicability and accuracy of cotton jam fault identification, solves the problem of that the cotton jam of the rolling machine cannot be identified in time, improves the cotton rolling efficiency, and ensures the operation safety of the rolling machine.

Description

Technical Field

[0001] This invention relates to the field of cotton gin safety monitoring technology, specifically to a method for identifying cotton gin faults based on current detection. Background Technology

[0002] A cotton gin is a type of cotton processing machinery used to separate lint from seed cotton. Commonly used gins include saw gins and roller gins. The saw gin utilizes a high-speed rotating (approximately 12-13 m / s) circular saw blade to hook and separate cotton fibers from the seed cotton through the gaps between the ribs. There are two types: brush-type and air-flow-type. Its main working components include feeding rollers, a cleaning mechanism, a ginning chamber, ginning ribs, a saw blade cylinder, a brush roller or air-flow suction nozzle, and a cotton collection box. Seed cotton is fed into the cleaning mechanism via paired feeding rollers, then enters the front chamber of the gin. It is thrown against the saw blade by the cotton-distributing rollers, while large debris such as bolls fall through. The seed cotton is hooked by the saw teeth and carried into the ginning chamber. The saw blade rotates rapidly, causing the mutually pulling seed cotton to form a rotating seed cotton lap. The saw teeth hook the fibers and rotate them. After passing through the gap between adjacent ginning ribs, the cotton fibers are brushed off by the brush roller (or airflow) and sent into the cotton collection box. The cotton seeds are blocked by the ribs and move down along the rib surface between the two saw blades. They are then discharged from the machine through the cotton seed comb.

[0003] During the operation of the cotton gin, cotton jamming is prone to occur at the junction of the saw blade cylinder and the ginning ribs. Once cotton jamming occurs, the cotton will heat up and catch fire in a very short time, causing equipment failure. Currently, cotton jamming is identified by manual observation. However, due to the limitations of human vision and the long reaction time of the human body, it is impossible to identify the problem in time and take relevant preventive measures. This leads to frequent occurrences of cotton jamming and fire in the cotton gin, reducing cotton ginning efficiency and posing safety hazards. Summary of the Invention

[0004] The purpose of this invention is to provide a fault identification method for cotton ginning machines based on current detection, so as to solve the problem of cotton jamming in cotton ginning machines not being identified in a timely manner.

[0005] To achieve the above objectives, the basic solution provided by this invention is: a fault identification method for a cotton ginning machine based on current detection, comprising:

[0006] S1: Obtain the real-time current signal of the saw-tooth cylinder inside the cotton gin;

[0007] S2: Input the real-time current signal into the working condition identification model, establish the current current change curve, and determine the current working condition of the cotton gin based on the current current change curve; the working condition of the cotton gin includes normal state, equipment short circuit state, and cotton jam state.

[0008] S3: If the cotton gin is stuck in a cotton jam state, the image of the current change curve is input into the preset convolutional neural network to determine the cotton jam position;

[0009] S4: Match the real-time current signal with the preset warning threshold at the corresponding cotton jamming location to determine the level of cotton jamming; wherein, the level of cotton jamming includes Level 1 cotton jamming and Level 2 cotton jamming.

[0010] S5: Based on the level and location of cotton jamming, determine the corresponding fault warning operation from the preset warning strategy, and issue a warning based on the fault warning operation.

[0011] It is understandable that the current will suddenly rise when the equipment is short-circuited or the motor is turned on. When the cotton gin jams, the rotation of the saw-tooth cylinder is obstructed, causing the current in the saw-tooth cylinder to rise. In order to distinguish the current fluctuation caused by cotton jamming and other conditions, this invention acquires the real-time current signal of the saw-tooth cylinder of the cotton gin in real time, analyzes the current signal using a working condition identification model, establishes the current current change curve, and determines the current working condition of the cotton gin based on the current current change curve. If the current working condition is cotton jamming, the image of the current change curve is input into a preset convolutional neural network to determine the jamming condition. The system first identifies the cotton jam location, then matches the real-time current signal with the preset warning threshold for the corresponding jam location to determine the jam severity level. Finally, based on the jam severity level and jam location, it determines the corresponding fault warning operation from the preset warning strategy. This allows for differentiated warnings based on different jam severity levels, enabling both location and severity analysis of the jam, thus improving the practicality and accuracy of jam fault identification. The fully automated identification and control process solves the problem of untimely jam identification in cotton ginning machines, improves ginning efficiency, and ensures the safe operation of the cotton ginning machine.

[0012] Preferably, determining the current operating condition in step S2 specifically includes the following steps:

[0013] Monitor the real-time current signal within a preset time period to obtain a real-time current signal set;

[0014] Based on the real-time current signal set, establish the current change curve;

[0015] The current operating condition of the cotton gin is determined by comparing the current change curve with the preset operating condition current curves in the operating condition identification model.

[0016] Understandably, using the normal operating current value of the cotton gin as a reference, the current rises rapidly during a short circuit, and the degree of current change is much higher than in other faults. When cotton is jammed, the current increases and remains at a high value, but the current in the sawtooth cylinder during a cotton jam is much lower than the current in the sawtooth cylinder during a short circuit. Therefore, this invention plots the real-time current signal as a current change curve. Using the various preset operating condition current curves in the operating condition identification model, the current operating condition of the cotton gin is determined, eliminating other operating condition factors that cause increased current and filtering out the current signal corresponding to the cotton jam fault.

[0017] Preferably, the construction of the working condition identification model specifically includes the following steps:

[0018] Acquire multiple sets of historical current signals under various operating conditions of the cotton gin;

[0019] Plot each set of historical current signals into a corresponding historical current curve;

[0020] The historical current curves are clustered to obtain the corresponding preset operating condition current curves for each operating condition, thereby completing the construction of the operating condition identification model.

[0021] By acquiring historical current parameters under various working conditions of the cotton gin, plotting historical current curves, and then classifying the curves using clustering, the preset working condition current curves corresponding to each working condition are obtained, resulting in a working condition identification model that can identify the working conditions of the cotton gin. This enables the screening of current signals corresponding to cotton jam faults while eliminating other working conditions that cause increased current, thus improving the accuracy of cotton jam identification.

[0022] Preferably, the pre-training of the convolutional neural network in step S3 specifically includes:

[0023] The serrated cylinder is divided into multiple detection areas;

[0024] Acquire historical current signals when cotton jamming faults occur in each detection area;

[0025] Based on historical current signals, establish historical cotton current curves for each detection area;

[0026] Based on the historical cotton current curves corresponding to each detection area, a training set and a validation set are established.

[0027] The convolutional neural network model is trained using the training set to obtain the trained convolutional neural network model;

[0028] The validation set is used to check whether the trained convolutional neural network model is qualified. If it is qualified, the convolutional neural network model is output; if it is not qualified, the convolutional neural network model is retrained using the training set until the convolutional neural network model is qualified.

[0029] To determine the location of cotton jamming at the junction of the sawtooth cylinder and the calendering ribs, this embodiment divides the sawtooth cylinder into multiple detection areas. Since the distance between each cotton jamming location and the critical location of the current path in the sawtooth cylinder is different, the current characteristics of different cotton jamming locations are different. Therefore, by acquiring the historical current signals when cotton jamming occurs in each detection area, a historical cotton jamming current curve corresponding to each detection area is established based on the historical current signals. Based on the historical cotton jamming current curves corresponding to each detection area, a training set and a validation set are established. The convolutional neural network is trained using the training set and the validation set to obtain a convolutional neural network that can determine the cotton jamming location in the sawtooth cylinder, thereby improving the accuracy of cotton jamming location determination.

[0030] Preferably, the pre-defined convolutional neural network model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer;

[0031] Step S3, which uses a pre-defined convolutional neural network model to determine the location of the cotton wadding, specifically includes the following steps:

[0032] The image of the current change curve is normalized to obtain standard image information;

[0033] The standard image information is input into the input layer;

[0034] The convolutional layer receives standard image information output from the input layer and uses a convolutional kernel of a preset size and the ReLU function as its activation function to extract features from the standard image information to obtain the initial image features;

[0035] The pooling layer receives the initial image features output by the convolutional layer and performs average pooling on the initial image features to obtain the target image features;

[0036] The fully connected layer receives the target image features output by the pooling layer, flattens the target image features into a one-dimensional vector, uses the Softmax function for classification, obtains the probability corresponding to each cotton jam position, selects the cotton jam position corresponding to the highest probability, and uses the cotton jam position corresponding to the highest probability as the current cotton jam position of the sawtooth cylinder of the cotton gin.

[0037] The output layer receives the cotton jam position from the fully connected layer and outputs the cotton jam position.

[0038] The convolutional neural network (CNN) model is configured with the following layers: input layer, convolutional layer, pooling layer, fully connected layer, and output layer. Since the CNN model uses gradient descent for learning, the input features need to be standardized. Therefore, this invention normalizes the current change curve image before it is input to the input layer to meet the data processing requirements of the CNN model. The standardized image information is then input to the input layer, which transmits the data to the convolutional layer. A pre-sized convolutional kernel and the ReLU function are used as activation functions for image feature extraction. The image features are then averaged through the pooling layer to obtain the target image features. These features are then input to the fully connected layer, which flattens them into a one-dimensional vector. The Softmax function is used for classification to determine the location of the cotton jam in the current ginning machine image. Finally, the output layer outputs the location of the cotton jam, thus locating the jam and avoiding the limitations of manual identification, thereby improving the efficiency and accuracy of cotton jam fault identification.

[0039] Preferably, the warning current threshold in step S4 includes a first-level cotton jamming current threshold and a second-level cotton jamming current threshold;

[0040] Determining the cotton jamming level in step S4 specifically includes the following steps:

[0041] The change in current is determined based on the real-time current signal;

[0042] The change in current was compared with the current threshold of the first-level cotton jamming and the current threshold of the second-level cotton jamming, respectively.

[0043] If the change in current is higher than the first-level cotton jamming current threshold but lower than the second-level cotton jamming current threshold, the current cotton gin is in the first-level cotton jamming state; if the change in current is higher than the second-level cotton jamming current threshold, the current cotton gin is in the second-level cotton jamming state.

[0044] By setting a cotton jam warning threshold, when the change in the current value corresponding to the real-time current signal is greater than the cotton jam threshold, it indicates that the cotton jam of the cotton gin has reached the first or second level. Differentiating the change in current is to more accurately identify the degree of cotton jam and provide a data basis for subsequent warnings.

[0045] Preferably, the fault warning operations corresponding to the first-level cotton jamming degree and cotton jamming location in the preset early warning strategy specifically include:

[0046] A primary signal light flashing command is generated and sent to the signal light, and a corresponding primary voice broadcast content is generated. The broadcast content is then broadcast using a broadcasting device to achieve primary signal light warning and primary voice broadcast warning. The primary voice broadcast content includes the location of the jammed cotton and the degree of jamming.

[0047] In the case of a primary cotton jam, the cotton ginning speed may slow down, but the cotton gin can still operate normally. The degree of failure is low. Therefore, this invention only provides voice broadcast warnings and signal light warnings to remind operators that the cotton gin may have a slight cotton jam.

[0048] Preferably, the fault warning operations corresponding to the secondary cotton jamming degree and cotton jamming location in the preset early warning strategy specifically include:

[0049] Generate and send the cotton ginning machine unpacking command to the cotton ginning machine, so that the cotton ginning machine can be unpacked;

[0050] A secondary signal light flashing command is generated and sent to the signal light, and a corresponding secondary voice broadcast content is generated. The broadcast content is then broadcast using a broadcasting device to achieve secondary signal light prompts and secondary voice broadcast prompts. The secondary voice broadcast content includes the location of the cotton jam and the degree of the secondary cotton jam.

[0051] In the secondary cotton jamming state, a large cotton ball may be stuck between the sawtooth cylinder and the ginning ribs, resulting in a significant reduction in cotton ginning speed. This invention directly controls the opening of the ginning machine and provides signal lights and voice prompts to remind operators to deal with the cotton jamming problem.

[0052] Preferably, step S3 further includes the following steps:

[0053] If the cotton gin is in a short circuit state, an unpacking command for the cotton gin is generated and sent to the cotton gin, causing the cotton gin to open.

[0054] A three-level traffic light flashing command is generated and sent to the traffic light, and a corresponding three-level voice broadcast content is generated. The broadcast content is then broadcast using a broadcasting device to achieve three-level traffic light prompts and three-level voice broadcast prompts.

[0055] When a short circuit occurs in the cotton gin, in order to protect the equipment, the cotton gin is opened for control, and the signal lights and voice broadcast system are activated to issue a fault alarm, so as to remind the operator that the equipment is short-circuited and needs to be repaired. Detailed Implementation

[0056] The present invention will be further described in detail below through specific embodiments:

[0057] This embodiment provides a fault identification method for cotton ginning machines based on current detection, including:

[0058] S1: Obtain the real-time current signal of the saw-tooth cylinder inside the cotton gin.

[0059] In this embodiment, an ammeter is installed at the sawtooth cylinder of the cotton gin to measure the real-time current signal of the sawtooth cylinder.

[0060] S2: Input the real-time current signal into the working condition identification model, establish the current current change curve, and determine the current working condition of the cotton gin based on the current current change curve; the working condition of the cotton gin includes normal state, equipment short circuit state, and cotton jam state.

[0061] The operating conditions of a cotton gin include normal operation, short circuit, and cotton jam. Using the current value of the cotton gin during normal operation as a reference, the current rises rapidly during a short circuit, and the degree of current change is much higher than in other faults. During a cotton jam, the current increases and remains at a high value, but the current in the sawtooth cylinder during a cotton jam is much lower than the current in the sawtooth cylinder during a short circuit. Therefore, the current operating condition of the cotton gin can be determined by analyzing the current change process.

[0062] The construction of the working condition identification model specifically includes: acquiring multiple sets of historical current signals under various working conditions of the cotton gin, plotting each set of historical current signals into a corresponding historical current curve, clustering the historical current curves to obtain the preset working condition current curve corresponding to each working condition, so as to complete the construction of the working condition identification model. This enables the selection of current signals corresponding to cotton jamming faults while eliminating other working conditions that cause increased current, thereby improving the accuracy of cotton jamming identification.

[0063] Understandably, in order to match the preset operating condition current curve in the operating condition identification model, this embodiment monitors the real-time current signal within a preset time period to obtain a real-time current signal set. Based on the real-time current signal set, a current change curve is established. Then, the current change curve is compared with each preset operating condition current curve in the operating condition identification model to determine the current operating condition corresponding to the cotton gin.

[0064] S3: If the cotton gin is stuck in a cotton jam state, the image of the current change curve is input into the preset convolutional neural network to determine the cotton jam position.

[0065] The pre-training of the convolutional neural network specifically includes: dividing the sawtooth cylinder into multiple detection regions, acquiring historical current signals when cotton jamming occurs in each detection region, establishing historical cotton jamming current curves corresponding to each detection region based on the historical current signals, establishing training and validation sets based on the historical cotton jamming current curves corresponding to each detection region, training the convolutional neural network model using the training set to obtain the trained convolutional neural network model, and using the validation set to check whether the trained convolutional neural network model is qualified. If qualified, the convolutional neural network model is output; if unqualified, the convolutional neural network model is retrained using the training set until the convolutional neural network model is qualified, thus obtaining a convolutional neural network that can determine the cotton jamming position of the sawtooth cylinder, improving the accuracy of cotton jamming position determination.

[0066] The pre-defined convolutional neural network model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer. The process of determining the location of the stuck cotton using the convolutional neural network specifically includes: Since the convolutional neural network model uses the gradient descent algorithm for learning, the input features need to be standardized. Therefore, this invention normalizes the image of the current change curve before it is input to the input layer to meet the data processing conditions of the convolutional neural network model. The standardized image information is then input to the input layer, which transmits the data to the convolutional layer. A pre-defined convolutional kernel and the ReLU function are used as activation functions for image feature extraction. The image is then averaged through the pooling layer to obtain the target image features, which are then input to the fully connected layer to flatten the target image features into a one-dimensional vector. The Softmax function is used for classification to obtain the location of the stuck cotton corresponding to the current ginning machine image. Finally, the output layer outputs the location of the stuck cotton, thus achieving accurate positioning of the stuck cotton, avoiding the limitations of current manual identification, and improving the efficiency and accuracy of stuck cotton fault identification. For example, in this embodiment, the layers of the convolutional neural network model are set as input layer, convolutional layer, pooling layer, convolutional layer, pooling layer... convolutional layer, pooling layer, fully connected layer, and output layer. A standard 32×32 image is input to the input layer. The convolutional layers use 5×5 kernels to convolve the image from the input layer, and then pass it through the ReLU activation function to obtain 20 two-dimensional feature maps of size 28×28. The pooling layers perform average pooling on all 2×2 sub-blocks in the convolutional layers to obtain 20 14×28 feature maps. A 2D feature map of size 14 is generated. The subsequent convolutional and pooling layers repeat the steps described above. Finally, 50 5×5 2D feature maps are obtained. A fully connected layer flattens these 50 5×5 2D feature maps into a one-dimensional vector. The Softmax function is used for classification to obtain the probability corresponding to each cotton jamming location. The location with the highest probability is selected as the cotton jamming location on the sawtooth drum corresponding to the current cotton ginning machine image. The output layer then outputs the cotton jamming location. The activation functions ReLU and Softmax are shown in Equations 1 and 2, respectively.

[0067] f(x)=max(0,x) (1)

[0068] Here, x is the input, and the output is the larger value between x and 0, which effectively solves the problem of gradient vanishing.

[0069]

[0070] Among them, z j Let represent the score of the j-th cotton level category, softmax(z). jThis represents the estimated probability of the j-th cotton jamming level category, where K is the dimension of the vector output by the softmax function, the sum of the vector elements is 1, and the final output is the probability value corresponding to each cotton jamming position.

[0071] S4: Match the real-time current signal with the preset warning threshold at the corresponding cotton jamming location to determine the cotton jamming severity level; wherein, the cotton jamming severity level includes Level 1 cotton jamming severity and Level 2 cotton jamming severity.

[0072] Specifically, based on the real-time current signal, the amount of current change is determined, and the amount of current change is compared with the warning current threshold to determine the level of cotton jamming. The level of cotton jamming is divided into Level 1 and Level 2. For example, when the current signal is set to a current change range of 5%-8%, it is Level 1 cotton jamming; when the current signal is set to a current change greater than 8%, it is Level 2 cotton jamming.

[0073] It is understood that in this embodiment, when it is determined that the cotton gin is in a short-circuit state, a cotton gin unpacking command is generated and sent to the cotton gin, causing the cotton gin to open. A three-level signal light flashing command is generated and sent to the signal light, and a corresponding three-level voice broadcast content is generated. The three-level voice broadcast content is broadcast using a broadcasting device to achieve three-level signal light prompts and three-level voice broadcast prompts. When it is determined that the cotton gin is in a short-circuit state, the signal light flashes blue, and the voice broadcast reads "Equipment short-circuit warning, please check".

[0074] S5: Based on the level and location of cotton jamming, determine the corresponding fault warning operation from the preset warning strategy, and issue a warning based on the fault warning operation.

[0075] This embodiment sets up different fault warning operations for different degrees and locations of cotton jamming, specifically:

[0076] The pre-defined early warning strategy for the first-level cotton jam severity and location involves the following steps: A first-level indicator light flashing command is generated and sent to the indicator light, along with a corresponding first-level voice broadcast message. This message is then broadcast using a broadcasting device, providing both first-level indicator light and voice broadcast warnings to alert operators that a minor cotton jam may have occurred in the cotton ginning machine. For example, when the x-th detection area of ​​the sawtooth cylinder is determined to be at the first-level cotton jam severity, the indicator light flashes yellow, and a voice broadcast announces, "A minor cotton jam has occurred in the x-th detection area of ​​the sawtooth cylinder; please check."

[0077] The pre-defined early warning strategy for a level 2 cotton jam condition involves the following steps: First, a command to open the ginning machine (1) is generated and sent to ginning machine 1, causing it to open. Then, a command to flash the secondary indicator light is generated and sent to the indicator light, along with corresponding secondary voice broadcast content. This voice broadcast is then used to alert the operator to address the cotton jam issue, providing both secondary indicator light and voice prompts. For example, when the x-th detection area of ​​the sawtooth cylinder is determined to be at level 2 cotton jam, the ginning machine is opened, the indicator light flashes red, and a voice broadcast announces, "Moderate cotton jam has occurred in the x-th detection area of ​​the sawtooth cylinder; please check."

[0078] This invention acquires the real-time current signal of the sawtooth cylinder of the cotton gin in real time, analyzes the current signal using a working condition identification model, establishes the current change curve, and determines the current working condition of the cotton gin based on the current change curve. If the current working condition is a cotton jam, the image of the current change curve is input into a preset convolutional neural network to determine the location of the cotton jam. Then, the real-time current signal is matched with a preset warning threshold for the corresponding cotton jam location to determine the degree of cotton jam. Finally, based on the degree of cotton jam and the location of the cotton jam, the corresponding fault warning operation is determined from the preset warning strategy to provide differentiated warnings according to different degrees of cotton jam. This not only enables the location of the cotton jam but also the analysis of the degree of cotton jam, improving the practicality and accuracy of cotton jam fault identification. The fully automated identification and control solves the problem of the inability to identify cotton jams in the cotton gin in a timely manner, improves cotton ginning efficiency, and ensures the safe operation of the cotton gin.

[0079] The above descriptions are merely embodiments of the present invention, and common knowledge regarding specific structures and characteristics is not elaborated upon here. It should be noted that those skilled in the art can make various modifications and improvements without departing from the structure of the present invention, and these should also be considered within the scope of protection of the present invention. These modifications and improvements will not affect the effectiveness of the present invention or the practicality of the patent. The scope of protection claimed in this application should be determined by the content of its claims, and the specific embodiments described in the specification can be used to interpret the content of the claims.

Claims

1. A fault identification method for a cotton ginning machine based on current detection, characterized in that, include: S1: Obtain the real-time current signal of the saw-tooth cylinder inside the cotton gin; S2: Input the real-time current signal into the working condition identification model, establish the current current change curve, and determine the current working condition of the cotton gin based on the current current change curve; wherein, the working condition of the cotton gin includes normal state, equipment short circuit state, and cotton jam state. S3: If the cotton gin is stuck in a cotton jam state, the image of the current change curve is input into a preset convolutional neural network to determine the cotton jam position; S4: Match the real-time current signal with the preset warning threshold of the corresponding cotton jamming location to determine the cotton jamming severity level; wherein, the cotton jamming severity level includes level one cotton jamming severity and level two cotton jamming severity. S5: Based on the level of cotton jamming and the location of cotton jamming, determine the corresponding fault warning operation from the preset warning strategy, and issue a warning based on the fault warning operation; The construction of the working condition identification model specifically includes the following steps: Acquire multiple sets of historical current signals under various operating conditions of the cotton gin; Plot each set of historical current signals into a corresponding historical current curve; The historical current curves are clustered to obtain the preset operating condition current curves corresponding to each operating condition, so as to complete the construction of the operating condition identification model. The pre-training of the convolutional neural network in step S3 specifically includes: The serrated cylinder is divided into multiple detection areas; Acquire historical current signals when cotton jamming faults occur in each of the aforementioned detection areas; Based on the historical current signals, establish the historical cotton current curves corresponding to each detection area; Based on the historical cotton current curves corresponding to each detection area, a training set and a validation set are established. The convolutional neural network model is trained using the training set to obtain the trained convolutional neural network model; The validation set is used to check whether the trained convolutional neural network model is qualified. If it is qualified, the convolutional neural network model is output; if it is not qualified, the convolutional neural network model is retrained using the training set until the convolutional neural network model is qualified.

2. The method for fault identification of a cotton ginning machine based on current detection according to claim 1, characterized in that... The determination of the current operating condition in step S2 specifically includes the following steps: Monitor the real-time current signal within a preset time period to obtain a real-time current signal set; Based on the real-time current signal set, establish the current change curve; The current operating condition of the cotton gin is determined by comparing the current current change curve with the preset operating condition current curves in the operating condition identification model.

3. The method for fault identification of a cotton ginning machine based on current detection according to claim 1, characterized in that, The preset convolutional neural network model includes an input layer, a convolutional layer, a pooling layer, a fully connected layer, and an output layer; Step S3, which uses a pre-defined convolutional neural network model to determine the location of the cotton wadding, specifically includes the following steps: The image of the current change curve is normalized to obtain standard image information; The standard image information is input into the input layer; The convolutional layer receives the standard image information output by the input layer, and uses a convolutional kernel of a preset size and the ReLU function as its activation function to extract features from the standard image information to obtain the initial image features; The pooling layer receives the initial image features output by the convolutional layer and performs average pooling on the initial image features to obtain the target image features; The fully connected layer receives the target image features output by the pooling layer, flattens the target image features into a one-dimensional vector, classifies them using the Softmax function, obtains the probability corresponding to each cotton jam position, filters out the cotton jam position corresponding to the highest probability, and uses the cotton jam position corresponding to the highest probability as the current cotton jam position of the sawtooth cylinder of the cotton gin. The output layer receives the cotton jam position output by the fully connected layer and outputs the cotton jam position.

4. The method for fault identification of a cotton ginning machine based on current detection according to claim 1, characterized in that, The warning current threshold in step S4 includes the first-level cotton jamming current threshold and the second-level cotton jamming current threshold; Determining the cotton jamming level in step S4 specifically includes the following steps: The change in current is determined based on the real-time current signal; The change in current is compared with the first-level cotton jamming current threshold and the second-level cotton jamming current threshold, respectively; If the change in current is higher than the first-level cotton jamming current threshold and lower than the second-level cotton jamming current threshold, the current cotton gin is in the first-level cotton jamming state; if the change in current is higher than the second-level cotton jamming current threshold, the current cotton gin is in the second-level cotton jamming state.

5. A method for fault identification of a cotton ginning machine based on current detection according to claim 1, characterized in that... The specific fault warning operations corresponding to the first-level cotton jamming degree and the cotton jamming location in the preset early warning strategy include: A primary signal light flashing command is generated and sent to the signal light, and a corresponding primary voice broadcast content is generated. The broadcast content is then broadcast using a broadcasting device to achieve primary signal light warning and primary voice broadcast warning. The primary voice broadcast content includes the location of the jammed cotton and the degree of jamming.

6. The method for fault identification of a cotton ginning machine based on current detection according to claim 1, characterized in that, The fault warning operations corresponding to the secondary cotton jamming degree and the cotton jamming location in the preset early warning strategy specifically include: Generate and send the cotton ginning machine unpacking command to the cotton ginning machine, so that the cotton ginning machine can be unpacked; A secondary signal light flashing command is generated and sent to the signal light, and a corresponding secondary voice broadcast content is generated. The broadcast content is then broadcast using a broadcasting device to achieve secondary signal light prompts and secondary voice broadcast prompts. The secondary voice broadcast content includes the location of the cotton jam and the degree of the secondary cotton jam.

7. The method for fault identification of a cotton gin based on current detection according to claim 1, characterized in that... Step S3 also includes the following steps: If the cotton gin is in a short circuit state, a cotton gin unpacking command is generated and sent to the cotton gin, causing the cotton gin to unpack. A three-level traffic light flashing command is generated and sent to the traffic light, and a corresponding three-level voice broadcast content is generated. The broadcast content is then broadcast using a broadcasting device to achieve three-level traffic light prompts and three-level voice broadcast prompts.

Images