Cotton gin fault identification method based on current detection

Abstract

The invention belongs to the technical field of cotton gin safety monitoring, and particularly discloses a cotton gin fault identification method based on current detection, which comprises the following steps: acquiring a real-time current signal of a sawtooth cylinder in a cotton gin, inputting the real-time current signal into a working condition identification model, and establishing a current change curve; and determining the current working condition of the cotton gin according to the current current change curve, if the cotton gin is in a cotton jamming state, inputting an image of the current change curve into a preset convolutional neural network, determining a cotton jamming position, matching the real-time current signal with a preset early warning threshold corresponding to the cotton jamming position, and determining the cotton jamming degree grade. And according to the cotton clamping fault state, determining a corresponding fault early warning operation from a preset early warning strategy, and performing early warning according to the fault early warning operation. Practicality and accuracy of cotton jamming fault identification are improved, the problem that cotton jamming of the cotton ginning machine cannot be identified in time is solved, cotton ginning efficiency is improved, and operation safety of the cotton ginning machine is guaranteed.

Description

Technical Field

[0001] The invention relates to the technical field of safety monitoring of cotton gins, and in particular to a cotton gin fault identification method based on current detection. Background Art

[0002] Cotton gin is a kind of cotton processing machinery, which is a machine for separating lint from cotton seed. Commonly used cotton gins include sawtooth cotton gin and roller cotton gin. Among them, the sawtooth cotton gin is a machine that uses a high-speed rotating (circumferential speed of about 12-13 m / s) disc saw blade to hook and pull cotton fibers through the gap between ribs to separate them from cotton seeds. There are two types of brush type and airflow type. Its main working parts include feeding rollers, cleaning mechanism, cotton ginning work box, cotton ginning ribs, saw blade cylinder, brush roller or airflow suction nozzle, cotton collecting box, etc. The cotton seed is fed into the cleaning mechanism through the paired feeding rollers, and then enters the front box of the cotton gin. It is thrown to the saw blade by the cotton picking roller, and large debris such as bell shells are leaked. The cotton seed is hooked by the saw teeth and brought into the cotton ginning work box. The saw blade rotates rapidly, driving the mutually pulled cotton seed to form a rotating cotton seed roll. The saw teeth hook the fiber and rotate. After passing through the gap between adjacent ginning ribs, the cotton fiber is brushed off by the brush roller (or airflow) and sent to the cotton collecting box; the cotton seeds are blocked by the ribs, move down along the rib surface between the two saw blades, and are discharged out of the machine through the cotton seed comb.

[0003] During the operation of the cotton gin, cotton jams are prone to occur at the junction of the saw blade cylinder and the gin ribs. Once cotton jams occur, the cotton will heat up and catch fire in a very short time, causing equipment failure. Currently, cotton jams are identified through manual observation. Due to the limited recognition of the human eye and the long reaction time of the human body, it is impossible to identify in time and perform relevant preventive operations, resulting in frequent cotton jams and fires in the cotton gin, which reduces the cotton ginning efficiency and poses a safety hazard. Summary of the invention

[0004] The object of the present invention is to provide a cotton gin fault identification method based on current detection to solve the problem that cotton jamming of the cotton gin cannot be identified in time.

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

[0006] S1: Get the real-time current signal of the sawtooth cylinder in 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 according to the current current change curve; wherein 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 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;

[0009] S4: matching the real-time current signal with the preset warning threshold of the corresponding cotton jam position to determine the cotton jam level; wherein the cotton jam level includes the first cotton jam level and the second cotton jam level;

[0010] S5: According to the cotton jam level and the cotton jam location, a corresponding fault warning operation is determined from the preset warning strategy, and a warning is issued according to the fault warning operation.

[0011] It is understandable that the current will suddenly rise when the equipment is short-circuited and the motor is turned on. When the cotton gin is jammed, the rotation of the serrated cylinder is hindered, causing the current of the serrated cylinder to increase. In order to distinguish the current fluctuation caused by the cotton jam fault and other conditions, the present invention obtains the real-time current signal of the serrated cylinder of the cotton gin in real time, analyzes the current signal using the working condition recognition model, establishes the current change curve, and determines the current working condition of the cotton gin according to the current current change curve. If the current working condition is a cotton jam state, the image of the current change curve is input into the preset convolutional neural network to determine the jam state. The cotton position is determined by the real-time current signal and the preset warning threshold of the corresponding cotton jam position to determine the degree of cotton jam. Finally, the corresponding fault warning operation is determined from the preset warning strategy according to the degree of cotton jam and the position of cotton jam, so as to make differentiated warnings according to the different degrees of cotton jam. It can not only locate the cotton jam position, but also analyze the degree of cotton jam, thereby improving the practicality and accuracy of cotton jam fault identification. The whole process is automatically identified and controlled, which solves the problem that cotton jam cannot be identified in time in the cotton gin, improves the cotton ginning efficiency, and ensures the safe operation of the cotton gin.

[0012] Preferably, the determination of 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] According to the real-time current signal set, establish the current current change curve;

[0015] The current working condition corresponding to the cotton gin is determined by comparing the current current change curve with each preset working condition current curve in the working condition identification model.

[0016] It can be understood that, taking the current value of the cotton gin in normal operation as a reference, the current rises rapidly when the equipment is in a short-circuit state, and the degree of current change is much higher than other faults. When the cotton is stuck, the current increases and remains at a high value, but the current of the sawtooth cylinder when the cotton is stuck is much smaller than the current of the sawtooth cylinder when the equipment is short-circuited. Therefore, the present invention plots the real-time current signal into a current change curve, and uses each preset working condition current curve in the working condition identification model to determine the current working condition corresponding to the cotton gin, so as to eliminate other working condition factors that cause the current to increase, and screen out the current signal corresponding to the cotton jam fault.

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

[0018] Obtain multiple groups of historical current signals under various working conditions of the cotton gin;

[0019] Plot each group 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 curve under each operating condition to complete the construction of the operating condition identification model.

[0021] By obtaining the historical current parameters of the cotton gin under various working conditions, drawing the historical current curve, and then classifying the curve by clustering, we can get the preset working condition current curve corresponding to each working condition, and get a working condition recognition model that can identify the working condition of the cotton gin. This realizes the screening of the current signal corresponding to the cotton jam fault under the premise of eliminating other working conditions that cause the current increase, thereby improving the accuracy of cotton jam identification.

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

[0023] Divide the sawtooth cylinder into multiple detection areas;

[0024] Obtain historical current signals when cotton jamming occurs in each detection area;

[0025] According to the historical current signal, establish the historical jam current curve corresponding to each detection area;

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

[0027] Using the training set to train the convolutional neural network model to obtain a trained convolutional neural network model;

[0028] The validation set is used to test whether the trained convolutional neural network model is qualified. If qualified, the convolutional neural network model is output; if unqualified, the training set is used again to train the convolutional neural network model until the convolutional neural network model is qualified.

[0029] In order to determine the position of the cotton jam at the junction of the serrated cylinder and the embossed ribs, the serrated cylinder is divided into multiple detection areas in this embodiment. Since the distances between each cotton jam position and the key position of the serrated cylinder current path are different, the current characteristics of different cotton jam positions are different. Therefore, by obtaining the historical current signals when cotton jams occur in each detection area, the historical cotton jam current curves corresponding to each detection area are established according to the historical current signals. Based on the historical cotton jam current curves corresponding to each detection area, a training set and a verification set are established. The convolutional neural network is trained using the training set and the verification set to obtain a convolutional neural network that can determine the cotton jam position of the serrated cylinder, thereby improving the accuracy of determining the cotton jam position.

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

[0031] The process of determining the location of the cotton jam using the preset convolutional neural network model in step S3 specifically includes the following steps:

[0032] Normalizing the image of the current variation curve to obtain standard image information;

[0033] Inputting the standard image information into the input layer;

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

[0035] The pooling layer receives the initial image features output by the convolution 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, and uses the Softmax function to classify them to obtain the probability corresponding to each cotton jam position, and selects the cotton jam position corresponding to the maximum probability, and uses the cotton jam position corresponding to the maximum probability as the cotton jam position of the current cotton gin serrated cylinder;

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

[0038] The layers in the convolutional neural network model are sequentially set to the input layer, the convolution layer, the pooling layer, the fully connected layer and the output layer. Since the convolutional neural network model uses the gradient descent algorithm for learning, the input features need to be standardized. Therefore, before the image of the current change curve is input to the input layer, the present invention performs normalization on the image of the current change curve to meet the data processing conditions of the convolutional neural network model, and then inputs the standard image information to the input layer. The input layer transmits the data to the convolution layer, and uses a convolution kernel of a preset size and a ReLU function as its activation function to extract image features. Then, the pooling layer performs average pooling processing to obtain target image features, and then inputs them to the fully connected layer to flatten the target image features into a one-dimensional vector, and uses the Softmax function for classification to obtain the cotton jam position corresponding to the current cotton gin image, and then uses the output layer to output the cotton jam position to achieve the positioning of the cotton jam position, avoid the limitations of current manual recognition, and improve the efficiency and accuracy of cotton jam fault recognition.

[0039] Preferably, the warning current threshold in step S4 includes a primary cotton jam current threshold and a secondary cotton jam current threshold;

[0040] The determination of the cotton jam level in step S4 specifically includes the following steps:

[0041] According to the real-time current signal, the current change is determined;

[0042] The current change is compared with the primary jam current threshold and the secondary jam current threshold respectively;

[0043] If the current change is higher than the first-level cotton jam current threshold and lower than the second-level cotton jam current threshold, the current cotton gin is at the first-level cotton jam level; if the current change is higher than the second-level cotton jam current threshold, the current cotton gin is at the second-level cotton jam level.

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

[0045] Preferably, the fault warning operations corresponding to the first-level cotton jam level and cotton jam position in the preset warning strategy specifically include:

[0046] Generate and send a first-level signal light flashing instruction to the signal light, and generate corresponding first-level voice broadcast content, and use the broadcasting equipment to broadcast according to the first-level voice broadcast content to achieve first-level signal light warning and first-level voice broadcast warning; wherein, the first-level voice broadcast content includes the cotton jam location and the first-level cotton jam degree.

[0047] In the first-level cotton jam state, the cotton ginning speed may slow down, but the cotton gin can still operate normally and the fault degree is low. Therefore, the present invention only performs voice broadcast warning and signal light warning to remind the operating worker that the cotton gin may have a slight cotton jam.

[0048] Preferably, the fault warning operations corresponding to the secondary cotton jam level and cotton jam position in the preset warning strategy specifically include:

[0049] Generate and send a cotton gin unpacking instruction to the cotton gin, so that the cotton gin unpacks;

[0050] Generate and send a secondary signal light flashing command to the signal light, and generate corresponding secondary voice broadcast content, and use the broadcasting equipment to broadcast according to the secondary voice broadcast content to realize secondary signal light prompts and secondary voice broadcast prompts; wherein, the secondary voice broadcast content includes the cotton jam location and the secondary cotton jam degree.

[0051] In the secondary cotton jam state, a large cotton ball may be stuck between the serrated cylinder and the cotton ginning ribs, resulting in a significant reduction in the cotton ginning speed. The present invention directly controls the cotton gin to open the box, and uses signal lights and voice broadcast prompts to prompt the operating workers to deal with the cotton jam problem.

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

[0053] If the cotton gin is in a short-circuit state, a cotton gin unpacking instruction is generated and sent to the cotton gin, so that the cotton gin is unpacked;

[0054] Generate and send a three-level signal light flashing instruction to the signal light, and generate corresponding three-level voice broadcast content. Use the broadcasting equipment to broadcast according to the three-level voice broadcast content to achieve three-level signal 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 unpacked and controlled, and the signal light and voice broadcast system are controlled to issue a fault alarm to remind the operator that the equipment is short-circuited and needs to be repaired. DETAILED DESCRIPTION

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

[0057] This embodiment provides a cotton ginning machine fault identification method based on current detection, comprising:

[0058] S1: Get the real-time current signal of the serrated cylinder in the cotton gin.

[0059] In this embodiment, an ammeter is arranged 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 according to the current current change curve; wherein the working condition of the cotton gin includes normal state, equipment short circuit state and cotton jam state.

[0061] The working conditions of the cotton gin include normal state, equipment short circuit state and cotton jam state. Taking the current value of the normal operation of the cotton gin as a reference, the current rises rapidly when the equipment is in short circuit state, and the degree of current change is much higher than that of other faults. When cotton jams, the current increases and remains at a high value, but the current of the serrated cylinder when cotton jams is much smaller than the current of the serrated cylinder when the equipment is short circuited. Therefore, the current change process can be analyzed to determine the current working condition of the cotton gin.

[0062] The construction of the operating condition identification model specifically includes: obtaining multiple groups of historical current signals under various operating conditions of the cotton gin, drawing each group of historical current signals into a corresponding historical current curve, clustering the historical current curves, and obtaining the corresponding preset operating condition current curve under each operating condition to complete the construction of the operating condition identification model. It is achieved that the current signal corresponding to the cotton jam fault is screened out under the premise of eliminating other operating conditions that cause the current to increase, thereby improving the accuracy of cotton jam identification.

[0063] It can be understood that 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, and establishes a current current change curve based on the real-time current signal set. Then, the current 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 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.

[0065] The pre-training of the convolutional neural network specifically includes: dividing the sawtooth cylinder into multiple detection areas, obtaining the historical current signal when the cotton jam fault occurs in each detection area, establishing the historical cotton jam current curve corresponding to each detection area according to the historical current signal, and establishing a training set and a verification set based on the historical cotton jam current curve corresponding to each detection area, using the training set to train the convolutional neural network model to obtain the trained convolutional neural network model, and using the verification set to check whether the trained convolutional neural network model is qualified. If qualified, the convolutional neural network model is output; if unqualified, the training set is re-used to train the convolutional neural network model until the convolutional neural network model is qualified, so as to obtain a convolutional neural network that can determine the cotton jam position of the sawtooth cylinder, thereby improving the accuracy of determining the cotton jam position.

[0066] The preset convolutional neural network model includes an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer. The process of determining the cotton jam position using the convolutional neural network specifically includes: since the convolutional neural network model uses a gradient descent algorithm for learning, the input features need to be standardized. Therefore, before the image of the current change curve is input to the input layer, the present invention performs normalization on the image of the current change curve to meet the data processing conditions of the convolutional neural network model, and then inputs the standard image information to the input layer. The input layer transmits the data to the convolution layer, and uses a convolution kernel of a preset size and a ReLU function as its activation function to extract image features. Then, the pooling layer performs average pooling processing to obtain target image features, and then inputs them to the fully connected layer to flatten the target image features into a one-dimensional vector, and uses the Softmax function for classification to obtain the cotton jam position corresponding to the current cotton gin image. Then, the output layer outputs the cotton jam position to achieve the positioning of the cotton jam position, avoid the limitations of current manual recognition, and improve the efficiency and accuracy of cotton jam fault recognition. For example, in this embodiment, the layers of the convolutional neural network model are set to input layer, convolution layer, pooling layer, convolution layer, pooling layer...convolution layer, pooling layer, full connection point and output layer, and a 32×32 standard image is input to the input layer. The convolution layer uses a 5×5 convolution kernel to convolve the image of the input layer, and then obtains 20 28×28 two-dimensional feature maps after the activation function ReLU. The pooling layer performs average pooling on all 2×2 sub-blocks in the convolution layer to obtain 20 14× 14-sized two-dimensional feature map, the following convolutional layer and pooling layer operation steps repeat the above steps; finally, 50 5×5-sized two-dimensional feature maps are obtained, and the fully connected layer flattens the target image features into a one-dimensional vector with 50 5×5-sized two-dimensional feature maps, and uses the Softmax function for classification to obtain the probability corresponding to each cotton jam position, and selects the cotton jam position corresponding to the maximum probability, and uses the cotton jam position corresponding to the maximum probability as the sawtooth cylinder cotton jam position corresponding to the current cotton gin image, and then uses the output layer to output the cotton jam position. Among them, the excitation function ReLU and the Softmax function are specifically shown in Formula 1 and Formula 2 respectively:

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

[0068] Among them, x is the input, and the output is a larger value between x and 0, which effectively solves the problem of gradient disappearance.

[0069]

[0070] Among them, z j represents the score of the j-th jam level category, softmax(z) jIt represents the estimated probability of the j-th cotton jamming degree category. K is the vector dimension output by the softmax function. The sum of the vector elements is 1. Finally, the probability values ​​corresponding to each cotton jamming position are output.

[0071] S4: Match the real-time current signal with the preset warning threshold of the corresponding cotton jam position to determine the cotton jam level; wherein the cotton jam level includes the first cotton jam level and the second cotton jam level.

[0072] Specifically, the current change is determined based on the real-time current signal, and the current change is compared with the warning current threshold to determine the degree of cotton jam. The cotton jam degree is divided into level one and level two. For example, when the current change is set to a current signal within the range of 5%-8%, it is level one; when the current change of the current signal is set to be greater than 8%, it is level two.

[0073] It can be understood that when the present embodiment determines that the cotton gin is in a state of equipment short circuit, it generates and sends a cotton gin unpacking instruction to the cotton gin, so that the cotton gin is unpacked, generates and sends a three-level signal light flashing instruction to the signal light, and generates a corresponding three-level voice broadcast content, and uses the broadcasting equipment to broadcast according to the three-level voice broadcast content to realize the three-level signal light prompt and the three-level voice broadcast prompt. When it is determined that the cotton gin is in a state of equipment short circuit, the signal light flashes blue, and the voice broadcast announces the content of "Equipment short circuit warning, please repair".

[0074] S5: According to the cotton jam level and the cotton jam location, a corresponding fault warning operation is determined from the preset warning strategy, and a warning is issued according to the fault warning operation.

[0075] This embodiment sets different fault warning operations according to different cotton jam levels and cotton jam locations. Specifically:

[0076] The fault warning operation corresponding to the first-level cotton jam level and cotton jam position in the preset warning strategy is: generate and send a first-level signal light flashing instruction to the signal light, and generate the corresponding first-level voice broadcast content, and use the broadcasting equipment to broadcast according to the first-level voice broadcast content, so as to realize the first-level signal light warning and the first-level voice broadcast warning to remind the operator that the cotton gin may have a slight cotton jam. For example, when it is determined that the x-th detection area of ​​the serrated cylinder is at the first-level cotton jam level, the signal light flashes yellow, and the voice broadcasts the prompt content "There is a slight cotton jam in the x-th detection area of ​​the serrated cylinder, please check".

[0077] The fault warning operation corresponding to the secondary cotton jam state in the preset warning strategy is: generate and send the cotton gin 1 unpacking instruction to the cotton gin 1, so that the cotton gin is unpacked, and then further generate and send the secondary signal light flashing instruction to the signal light, and generate the corresponding secondary voice broadcast content, and use the broadcasting equipment to broadcast according to the secondary voice broadcast content, so as to realize the secondary signal light prompt and the secondary voice broadcast prompt, and prompt the operator to deal with the cotton jam problem. For example, when it is determined that the xth detection area of ​​the serrated cylinder is at the second level of cotton jam, the cotton gin is controlled to unpack, the signal light flashes red, and the voice broadcasts the prompt content of "moderate cotton jam occurs in the xth detection area of ​​the serrated cylinder, please check".

[0078] The present embodiment of the invention obtains the real-time current signal of the serrated cylinder of the cotton gin in real time, analyzes the current signal using the working condition recognition model, establishes the current change curve, and determines the current working condition of the cotton gin according to the current 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 cotton jam position, and then the real-time current signal is matched with the preset warning threshold corresponding to the cotton jam position to determine the cotton jam degree level. Finally, according to the cotton jam degree level and the cotton jam position, the corresponding fault warning operation is determined from the preset warning strategy, so as to provide differentiated warnings according to different cotton jam degrees. It can not only locate the cotton jam position, but also analyze the cotton jam degree, thereby improving the practicality and accuracy of cotton jam fault identification. The whole process is automatically identified and controlled, which solves the problem that cotton jams cannot be identified in time in the cotton gin, improves the cotton ginning efficiency, and ensures the safe operation of the cotton gin.

[0079] The above is only an embodiment of the present invention, and the common knowledge such as the known specific structure and characteristics in the scheme is not described in detail here. It should be pointed out that for those skilled in the art, several deformations and improvements can be made without departing from the structure of the present invention, which should also be regarded as the protection scope of the present invention, and these will not affect the effect of the implementation of the present invention and the practicality of the patent. The scope of protection required by this application shall be based on the content of its claims, and the specific implementation methods and other records in the specification can be used to interpret the content of the claims.

Claims

1. A cotton ginning machine fault identification method based on current detection, characterized in that: include: S1: Get the real-time current signal of the sawtooth cylinder in the cotton gin; S2: inputting the real-time current signal into the working condition identification model, establishing a current current change curve, and determining the current working condition of the cotton gin according to the current current change curve; wherein the working condition of the cotton gin includes a normal state, an equipment short circuit state, and a cotton jam state; S3: If the cotton gin is in a cotton jam state, inputting the image of the current change curve into a preset convolutional neural network to determine the cotton jam position; S4: matching the real-time current signal with a preset warning threshold corresponding to the cotton jam position to determine the cotton jam level; wherein the cotton jam level includes a first cotton jam level and a second cotton jam level; S5: According to the cotton jam level and the cotton jam position, a corresponding fault warning operation is determined from a preset warning strategy, and a warning is issued according to the fault warning operation.

2. A cotton ginning machine fault identification method based on current detection according to claim 1, characterized in that ,The determination of the current working 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; Establishing a current current variation curve according to the real-time current signal set; The current operating condition corresponding to the cotton gin is determined by comparing the current current variation curve with each preset operating condition current curve in the operating condition identification model.

3. A cotton ginning machine fault identification method based on current detection according to claim 1, characterized in that: The construction of the working condition identification model specifically includes the following steps: Obtain multiple groups of historical current signals under various working conditions of the cotton gin; Plot each group of historical current signals into a corresponding historical current curve; The historical current curves are clustered to obtain the preset operating condition current curve corresponding to each operating condition, so as to complete the construction of the operating condition identification model.

4. A cotton ginning machine fault identification method based on current detection according to claim 1, characterized in that: The pre-training of the convolutional neural network in step S3 specifically includes: Divide the sawtooth cylinder into multiple detection areas; Acquire historical current signals when cotton jamming failure occurs in each of the detection areas; According to the historical current signal, a historical jam current curve corresponding to each detection area is established; Based on the historical jam current curves corresponding to each detection area, a training set and a validation set are established; Using the training set to train the convolutional neural network model to obtain a trained convolutional neural network model; The validation set is used to check whether the trained convolutional neural network model is qualified. If qualified, the convolutional neural network model is output; if unqualified, the training set is re-used to train the convolutional neural network model until the convolutional neural network model is qualified.

5. A cotton ginning machine fault identification method based on current detection according to claim 1, characterized in that: The preset convolutional neural network model includes an input layer, a convolution layer, a pooling layer, a fully connected layer and an output layer; The process of determining the location of the cotton jam using the preset convolutional neural network model in step S3 specifically includes the following steps: Normalizing the image of the current variation curve to obtain standard image information; Inputting the standard image information into the input layer; The convolution layer receives the standard image information output by the input layer, and uses a convolution kernel of a preset size and a ReLU function as its activation function to extract features from the standard image information to obtain initial features of the image; The pooling layer receives the initial image features output by the convolution layer, and performs average pooling processing on the initial image features to obtain 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, screens out the cotton jam position corresponding to the maximum probability, and uses the cotton jam position corresponding to the maximum probability as the cotton jam position of the current cotton gin serrated cylinder; The output layer receives the cotton jam position output by the fully connected layer, and outputs the cotton jam position.

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

7. A method for identifying faults of a cotton gin based on current detection according to claim 1, characterized in that The fault warning operations corresponding to the first-level cotton jam level and the cotton jam position in the preset warning strategy specifically include: Generate and send a first-level signal light flashing instruction to the signal light, and generate corresponding first-level voice broadcast content, and use the broadcasting equipment to broadcast according to the first-level voice broadcast content to achieve first-level signal light warning and first-level voice broadcast warning; wherein, the first-level voice broadcast content includes the cotton jam location and the first-level cotton jam degree.

8. A cotton ginning machine fault identification method based on current detection according to claim 1, characterized in that: The fault warning operations corresponding to the secondary cotton jam level and the cotton jam position in the preset warning strategy specifically include: Generate and send a cotton gin unpacking instruction to the cotton gin, so that the cotton gin unpacks; Generate and send a secondary signal light flashing instruction to the signal light, and generate corresponding secondary voice broadcast content, and use the broadcast device to broadcast according to the secondary voice broadcast content to achieve secondary signal light prompts and secondary voice broadcast prompts; wherein, the secondary voice broadcast content includes the cotton jam location and the secondary cotton jam degree.

9. A cotton ginning machine fault identification method based on current detection according to claim 1, characterized in that ,Step S3, further comprises the following steps: If the cotton gin is in a short-circuit state, a cotton gin unpacking instruction is generated and sent to the cotton gin, so that the cotton gin is unpacked; Generate and send a three-level signal light flashing instruction to the signal light, and generate corresponding three-level voice broadcast content, and use the broadcast device to broadcast according to the three-level voice broadcast content to achieve three-level signal light prompts and three-level voice broadcast prompts.

Images