Photovoltaic slicing machine cutting line state detection system and method

Abstract

The application discloses a kind of photovoltaic slicer cutting line state detection system and method, the system includes detection module and data processing module, detection module is used to obtain the state data of cutting line, state data includes at least 3 in the following: cutting line tension, vibration frequency, temperature, cutting speed, diameter and surface scratch quantity;Data processing module is used to determine whether cutting line is in early warning state according to state data;If cutting line is in early warning state, then data processing module is also used to determine the running state of cutting line according to state data, running state includes: normal, abnormal early warning, emergency failure.The system provided by the application has strong real-time performance and wide application range.

Description

Technical Field

[0001] This invention belongs to the field of photovoltaic processing technology, specifically relating to a photovoltaic slicing machine cutting line status detection system and method. Background Technology

[0002] In the photovoltaic slicing process, the condition of the cutting wire (such as diamond wire) directly affects the slice pass rate and production efficiency. Wire breakage can lead to the scrapping of a batch of silicon material. Therefore, the detection of the cutting wire condition is a key link in photovoltaic production.

[0003] Traditional methods for detecting the condition of cutting wires primarily rely on images or data from multiple sensors to detect wire breakage. This approach is relatively crude, only issuing warnings when the cutting wire breaks, and exhibits significant latency. To address this, researchers have developed a method capable of predicting the wear condition of cutting wires. This method is mainly designed for conductive cutting wires, determining the wear condition and breakage status by dividing the current flowing through the wire by its resistance. However, it cannot detect the condition of non-conductive cutting wires.

[0004] Therefore, current methods for detecting the state of cutting lines suffer from problems such as strong lag or narrow applicability. Summary of the Invention

[0005] This invention provides a photovoltaic slicing machine cutting line status detection system and method, which can solve the above-mentioned technical problems.

[0006] In a first aspect, an embodiment of the present invention provides a photovoltaic slicing machine cutting line status detection system, comprising:

[0007] The detection module is used to acquire the status data of the cutting line, wherein the status data includes at least three of the following: tension of the cutting line, vibration frequency, temperature, cutting speed, diameter and number of surface scratches.

[0008] A data processing module is used to determine whether the cutting line is in a warning state based on the status data.

[0009] If the cutting line is in an early warning state, the data processing module is further used to determine the operating state of the cutting line based on the state data, wherein the operating state includes: normal, abnormal early warning, and emergency fault.

[0010] Secondly, embodiments of the present invention provide a method for detecting the cutting line status of a photovoltaic slicing machine, including:

[0011] Acquire the status data of the cutting line, wherein the status data includes at least three of the following: tension of the cutting line, vibration frequency, temperature, cutting speed, and image;

[0012] Based on the status data, determine whether the cutting line is in a warning state;

[0013] If the cutting line is in an early warning state, the operating status of the cutting line is determined based on the status data, wherein the operating status includes: normal, abnormal warning, and emergency fault.

[0014] The beneficial effects of this invention compared to existing technologies are as follows: This invention constructs a multi-dimensional sensing system by simultaneously monitoring multiple physical parameters of the cutting wire, including tension, vibration frequency, temperature, cutting speed, diameter, and surface scratches. These parameters exhibit a synergistic evolution pattern during the cutting wire wear process. For example, abnormal fluctuations in tension are often accompanied by changes in the vibration spectrum, while the increase in temperature is intrinsically related to the accumulation of cutting speed and surface scratches. By comprehensively analyzing these interrelated dynamic data, the data processing module can capture early abnormal features that cannot be reflected by a single indicator, thereby identifying the gradual evolution process from normal state to abnormal warning and even emergency failure. This multi-parameter fusion-based evaluation mechanism enables the system to issue early warnings at an early stage before the cutting wire performance significantly deteriorates or breaks. Since this invention relies entirely on the analysis of physical behavior and does not involve electrical properties, its application is not limited by the conductivity of the cutting wire material, achieving universal monitoring and early protection for various types of cutting wire conditions. Attached Figure Description

[0015] Figure 1 A flowchart illustrating the implementation of a photovoltaic slicing machine cutting line status detection method provided in an embodiment of the present invention;

[0016] Figure 2 A flowchart illustrating the implementation of a method for determining the early warning state of a cutting line according to an embodiment of the present invention;

[0017] Figure 3 A flowchart illustrating the implementation of a method for determining the running state of a cutting line according to an embodiment of the present invention;

[0018] Figure 4 This is a schematic diagram of a photovoltaic slicing machine cutting line status detection system provided in an embodiment of the present invention. Detailed Implementation

[0019] In the following description, specific details such as particular system architectures and techniques are set forth for illustrative purposes and not for limitation, in order to provide a thorough understanding of the embodiments of the invention. However, those skilled in the art will understand that the invention can be implemented in other embodiments without these specific details. In other instances, detailed descriptions of well-known systems, apparatuses, circuits, and methods are omitted so as not to obscure the description of the invention with unnecessary detail.

[0020] It should be understood that, when used in this specification and the appended claims, the term "comprising" indicates the presence of the described features, integrals, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components and / or collections thereof.

[0021] It should also be understood that the term “and / or” as used in this specification and the appended claims refers to any combination of one or more of the associated listed items and all possible combinations, and includes such combinations.

[0022] As used in this specification and the appended claims, the term "if" may be interpreted, depending on the context, as "when," "once," "in response to determination," or "in response to detection." Similarly, the phrase "if determined" or "if [described condition or event] is detected" may be interpreted, depending on the context, as meaning "once determined," "in response to determination," "once [described condition or event] is detected," or "in response to detection of [described condition or event]."

[0023] Furthermore, in the description of this invention and the appended claims, the terms "first," "second," "third," etc., are used only to distinguish descriptions and should not be construed as indicating or implying relative importance.

[0024] References to "one embodiment" or "some embodiments" as described in this specification mean that one or more embodiments of the invention include a specific feature, structure, or characteristic described in connection with that embodiment. Therefore, the phrases "in one embodiment," "in some embodiments," "in other embodiments," "in still other embodiments," etc., appearing in different parts of this specification do not necessarily refer to the same embodiment, but rather mean "one or more, but not all, embodiments," unless otherwise specifically emphasized. The terms "comprising," "including," "having," and variations thereof mean "including but not limited to," unless otherwise specifically emphasized.

[0025] The present invention will be further described in detail below with reference to specific embodiments, but the implementation of the present invention is not limited thereto.

[0026] Example 1

[0027] Figure 1 The diagram illustrates a flowchart of a photovoltaic slicing machine cutting line status detection method according to an embodiment of the present invention. As an example and not a limitation, this method can be applied to the photovoltaic slicing machine cutting line status detection system shown in Embodiment 4 below. The method may include steps S101 to S103. Each step is described below.

[0028] S101, obtain the status data of the cutting line.

[0029] For example, the status data of the cutting wire may include at least three of the following: cutting wire tension, vibration frequency, temperature, cutting speed, diameter, and number of surface scratches.

[0030] For example, the diameter of the cutting line and the number of surface scratches can be determined based on the acquired image of the cutting line.

[0031] Specifically, the diameter of the cutting line can be determined based on its edge. The grayscale value of the edge of the cutting line in the image of the cutting line is less than or equal to half of the center grayscale value. The area where the surface scratch is located must include at least N consecutive adjacent pixels in the image of the cutting line whose grayscale difference is greater than or equal to a grayscale difference threshold, where N is a positive integer, such as 5. The center grayscale value refers to the average grayscale value of the area where the cutting line is located.

[0032] S102, Based on the status data, determine whether the cutting line is in a warning state.

[0033] In one possible implementation, to avoid performing the complex data processing steps in the subsequent step S103 multiple times, a simple preliminary screening can be performed using the status data to determine whether the cutting line is in a warning state; if the cutting line is in a warning state, then step S103 can be performed.

[0034] In one example, the presence or absence of a cutting wire can be determined based on its tension, vibration frequency, and diameter.

[0035] In another example, the status of the cutting line in a warning state can be determined based on the tension of the cutting line, the cutting speed, and the number of surface scratches.

[0036] In yet another example, it can be determined whether the cutting line is in a warning state based on the tension of the cutting line, or the cutting speed and high-frequency components of vibration.

[0037] In another possible implementation, if the cutting line is not in a warning state, the process can return to step S101 to obtain the status data for the next cycle.

[0038] S103, determine the operating status of the cutting line based on the status data.

[0039] For example, the operating status of the cutting line may include: normal, abnormal warning, and emergency fault.

[0040] For example, a normal state indicates that the cutting wire is operating normally. Although it previously entered a warning state, the slicer might be running a new task and still using the threshold from the previous task, causing the warning to malfunction. An abnormal warning indicates that the cutting wire is severely worn and at risk of breakage, but it can still perform the cutting task. An emergency failure indicates that the cutting wire is broken or on the verge of breakage, and the cutting task can no longer be performed.

[0041] In one example, the feature score of each state data can be calculated based on the state data threshold corresponding to various state data. Then, the correlation between each pair of state data can be calculated based on the feature score. The real-time weight of each state data can be determined based on the correlation. The real-time state score of the cutting line can be calculated based on the real-time weight and the feature score, and then corrected based on the historical trend. Finally, the running status of the cutting line can be determined based on the warning interval in which the corrected real-time state score is located.

[0042] For example, the threshold values ​​for the state data such as tension, vibration frequency, temperature, cutting speed, diameter, and number of surface scratches can be: tension threshold, frequency threshold, temperature threshold, diameter change ratio threshold, and maximum number of scratches threshold, respectively.

[0043] Generally, the threshold for state data is within the normal range of such state data, such as the average of the upper and lower limits.

[0044] This invention constructs a multi-dimensional sensing system by simultaneously monitoring multiple physical parameters of the cutting wire, including tension, vibration frequency, temperature, cutting speed, diameter, and surface scratches. These parameters exhibit a synergistic evolution pattern during the cutting wire wear process. For example, abnormal fluctuations in tension are often accompanied by changes in the vibration spectrum, while increases in temperature are intrinsically correlated with cutting speed and the accumulation of surface scratches. By comprehensively analyzing these interrelated dynamic data, the data processing module can capture early abnormal features that cannot be reflected by a single indicator, thereby identifying the gradual evolution process from normal state to abnormal warning and even emergency failure. This multi-parameter fusion-based evaluation mechanism enables the system to issue early warnings at an early stage before significant degradation or breakage of the cutting wire performance. Since this invention relies entirely on the analysis of physical behavior and does not involve electrical properties, its application is not limited by the conductivity of the cutting wire material, achieving universal monitoring and early protection for various types of cutting wire conditions.

[0045] Furthermore, if the state of the cutting line is screened only by static rules, there is a risk that it will be impossible to distinguish between instantaneous interference and real fault trends, resulting in a large number of meaningless alarms. If the state data of each batch of samples is divided into states, it will also cause serious computational delays and waste of resources. The present invention achieves a balance between detection accuracy and computational efficiency by first screening according to static rules and then dividing the state when the probability of fault is high.

[0046] Example 2

[0047] Figure 2 The diagram illustrates a flowchart of a method for determining the early warning state of a cutting line according to an embodiment of the present invention. This method is an example, not a limitation, and represents one possible specific implementation of step S102 described above. The method may include steps S201 to S207, which are described below.

[0048] S201, determine whether the correlation coefficient between the tension of the cutting line and the cutting speed is less than the correlation threshold.

[0049] In one example, if the correlation coefficient between the tension of the cutting line and the cutting speed is less than the correlation threshold, then step S202 can be performed.

[0050] For example, the correlation coefficient between the tension of the cutting line and the cutting speed can be the Pearson coefficient between the two.

[0051] For example, the relevance threshold can be 0.5.

[0052] The correlation coefficient between the tension of the cutting wire and the cutting speed can characterize the slicing machine's control sensitivity over the cutting wire. When abnormalities occur in the process, such as uneven processing of the crystal rod material or problems with coolant spraying, the slicing machine's control over the cutting wire will weaken, causing the correlation coefficient between the two to drop sharply.

[0053] In another example, if the correlation coefficient between the tension of the cutting line and the cutting speed is not less than the correlation threshold, the process can be terminated and step S101 can be performed.

[0054] S202, determine whether the number of surface scratches on the cutting line is greater than the maximum number of scratches threshold.

[0055] In one example, if the number of surface scratches on the cutting line is greater than the maximum number of scratches threshold, step S203 can be performed to determine that the cutting line is in a warning state.

[0056] Industrial data measurements show that surface damage accumulates before most cutting wires break. The correlation coefficient between cutting wire tension and cutting speed being less than the correlation threshold could also be caused by momentary jamming of the tensioning mechanism in the slicing machine, resulting in a certain false positive rate. Further screening using the number of surface scratches can reduce this false positive rate. Furthermore, combined screening using the correlation coefficient and the number of scratches can provide early warning of cutting wire failures caused by external factors, such as the presence of hard impurities within the processed crystal ingot or surface damage to the slicing machine guide rollers.

[0057] In another example, if the number of surface scratches on the cutting line is not greater than the maximum number of scratches threshold, the process can be terminated and step S101 above can be performed to obtain the status data for the next cycle.

[0058] S203, confirming that the cutting line is in a warning state.

[0059] For example, while performing step S201, the following step S204 can be performed.

[0060] S204, determine whether the tension of the cutting wire is within the normal range.

[0061] For example, the upper and lower limits of the normal tension range can be equal to the tension thresholds of a first preset multiple and a third preset multiple, respectively. For instance, the normal tension range is [0.5...]. ], 1.2 and 0.5 are the first and third preset multiples, respectively. This is the tension threshold.

[0062] In one example, if the tension of the cutting line is less than its normal range, it indicates that the slicer has malfunctioned in controlling the cutting line. In this case, step S203 can be performed directly to determine that the cutting line is in a warning state.

[0063] In another example, if the tension of the cutting line exceeds its normal range, step S205 can be performed.

[0064] In another example, if the tension of the cutting line is within its normal range, the process can be terminated, and step S101 above can be performed to obtain the status data for the next cycle.

[0065] S205, determine whether the rate of change of the diameter of the cutting line is within the general warning range.

[0066] In one example, wear typically occurs during normal operation of the cutting wire, leading to a reduction in its diameter. However, this process is slow, and the rate of change in the wire's diameter stabilizes within a fixed range. When the cutting wire is nearing breakage, the rate of change in diameter abruptly changes. Therefore, by determining whether the rate of change in the wire's diameter falls within the general warning range, the cause of the abnormal wire tension can be further identified. If the rate of change in the wire's diameter exceeds the general warning range, step S206 can be performed for further screening using the high-frequency components of the cutting wire's vibration.

[0067] For example, the upper limit of the general warning range for the diameter change rate can be equal to a diameter change ratio threshold that is a fourth preset multiple, and the lower limit can be equal to the diameter change ratio threshold. For instance, the general warning range for the diameter change rate is […]. ], 4 is the fourth preset multiple, This is the threshold for the proportion of diameter change.

[0068] In another example, if the rate of change of the diameter of the cutting line is within the general warning range, the following step S207 can be performed to further screen the line by the vibration frequency of the cutting line.

[0069] In another example, if the rate of change of the diameter of the cutting line is less than the general warning range, it means that the cutting line is working normally, and the process can be terminated and step S101 can be performed to obtain the status data of the next cycle.

[0070] S206, determine whether the high-frequency component of the vibration of the cutting line is greater than the high-frequency component threshold.

[0071] In one example, if the high-frequency component of the vibration of the cutting line is greater than the high-frequency component threshold, the above step S203 can be performed to determine that the cutting line is in a warning state.

[0072] By using tension, diameter change rate, and high-frequency vibration components, we can screen out situations where the cutting wire is about to break. A large diameter change rate indicates that the cutting wire is being rapidly peeled off or is experiencing severe local damage. High-frequency vibration indicates that the cutting wire is undergoing violent impact and friction with the crystal rod being processed. High tension is another important indicator of the occurrence of these two phenomena.

[0073] Using only thresholds for tension, diameter change rate, and vibration frequency to screen for faults will result in a high false alarm rate. When the vibration source is not the cutting wire itself—for example, when the slicer experiences poor lubrication in its bearings, guide rails, or electrodes—vibration exceeding the threshold will trigger an alarm. Although the cutting wire's tension and diameter change rate may be slightly high at this point, it is still in the normal wear process and has not yet reached the critical replacement standard. Issuing an alarm at this time will lead to unclear fault location and material waste.

[0074] In another example, if the high-frequency component of the vibration of the cutting line is not greater than the high-frequency component threshold, the process can be terminated and the above step S101 can be performed.

[0075] S207, determine whether the vibration frequency of the cutting line is greater than the second preset multiple frequency threshold.

[0076] In one example, if the vibration frequency of the cutting line is greater than the second preset multiple of the frequency threshold, the above step S203 can be performed to determine that the cutting line is in a warning state.

[0077] For example, the second preset multiple can be 1.1.

[0078] By screening for tension, diameter change rate, and vibration frequency, typical aging phenomena of the cutting wire under normal but high-intensity operation can be identified. When this occurs, it indicates that the cutting wire is undergoing steady wear and its performance is about to decline to a critical value.

[0079] In another example, if the vibration frequency of the cutting line is not greater than the second preset multiple of the frequency threshold, the process can be terminated and the above step S101 can be performed.

[0080] The above screening process can provide accurate early warning of the cutting line's condition, laying a solid foundation for subsequent determination of the cutting line's condition.

[0081] Example 3

[0082] Figure 3 The diagram illustrates a flowchart of a method for determining the operating state of a cutting line according to an embodiment of the present invention. This method is an example, not a limitation, and is a possible specific implementation of step S103 in embodiment 1 above. The method may include steps S301 to S306, which are described below.

[0083] S301, Calculate the feature score for each type of state data based on the state data threshold.

[0084] In one example, the feature score of the state data can be calculated using the following formula:

[0085]

[0086] in, For the first Feature scores of state data, For the first The numerical values ​​of the state data, For the first The difference between the upper and lower limits of the normal range interval for this type of state data. No. Threshold for various state data Outbound penalty parameters, This refers to the steepness parameter of the transition zone.

[0087] in:

[0088]

[0089] in, The amplitude coefficient of the Gaussian modulation is... The width parameter of the Gaussian function. This is the center position of the Gaussian function.

[0090] When the state data approaches the critical point hour, Automatically increases in size, significantly enhancing the detection sensitivity of the area, generally These represent the upper and lower limits of the normal range. Gaussian modulation is used to determine the feature scores of each state data, enabling targeted enhanced detection in specific physical critical regions.

[0091] S302, calculate the correlation between each pair of state data based on feature scores.

[0092] In one example, the correlation between state data can be calculated using the following formula:

[0093]

[0094] in, For the first State data and the first The correlation between the state data These are the mixed weighting coefficients.

[0095] in:

[0096]

[0097]

[0098]

[0099] in, For the first This type of state data is in the current collection cycle. Feature scores at each time point For the first The average feature score of the data in the current collection period. This represents the total number of sampling points in one sampling period. , is the time decay constant. , The first Type of state data, the first The feature score of the state data is distributed in the current collection period.

[0100] S303, determine the real-time weight of each state data based on the correlation degree.

[0101] In one example, the real-time weight of the state data can be calculated using the following formula:

[0102]

[0103]

[0104] in, For the first Real-time weights of various state data The first of the correlation matrix The correlation matrix consists of eigenvalues ​​and eigenvalues. constitute.

[0105] By dynamically adjusting the weight of each feature parameter in the final evaluation, it is possible to ensure that important features or associated abnormal features contribute more to the total score, thereby improving the sensitivity of detection to deep faults.

[0106] S304, determine the real-time state score of the cutting line based on the feature score and real-time weight.

[0107] In one example, the real-time status score of the cutting line can be calculated using the following formula.

[0108]

[0109] in, The real-time status score of the cutting line is given. This represents the total number of state data types. This is a dispersion adjustment factor that controls the impact of feature score dispersion on the results.

[0110] S305, corrects the real-time state score based on the historical trend of the state score of the cutting line, and obtains the corrected real-time state score.

[0111]

[0112]

[0113] in, This is the corrected real-time status score. , These are the mean and standard deviation of the historical state scores, respectively. For trend weight parameters, For integration weight parameters, This represents the average slope of the real-time status score from the previous period.

[0114] By correcting real-time status scores based on historical trends, score changes can be made more robust. This maintains a positive correlation between deviation and score while incorporating historical experience and cumulative effects, making early warning results more forward-looking and reliable.

[0115] S306, determine the operating status of the cutting line based on the warning range in which the corrected real-time status score is located.

[0116] For example, the warning intervals can correspond one-to-one with the types of operating states, and no two warning intervals can overlap.

[0117] For example, the warning range for "normal" could be [0, 0.5), the warning range for "abnormal warning" could be [0.5, 0.8), and the warning range for "emergency fault" could be [0.8, 1].

[0118] This invention improves the detection system by nonlinear characterization of deviations, dynamic weighting to highlight correlation anomalies, and dispersion penalty to focus on local risks. Finally, it integrates historical baselines and cumulative effects for correction, enabling the detection system to keenly identify early hidden faults and achieve a leap from "post-event alarm" to "pre-event warning".

[0119] Example 4

[0120] Figure 4 The diagram shown illustrates the structure of a photovoltaic slicing machine cutting line status detection system according to an embodiment of the present invention. As an example and not a limitation, the system may include a detection module 410 and a data processing module 420.

[0121] In one possible implementation, the detection module 410 can acquire the status data of the cutting line, and the data processing module 420 can determine whether the cutting line is in a warning state based on the status data; if the cutting line is in a warning state, the data processing module 420 is also used to determine the operating state of the cutting line based on the status data.

[0122] For example, the detection module 410 and the data processing module 420 can respectively execute steps S101, S102 and S103 in the above embodiment 1.

[0123] Optionally, the data processing module may execute steps S102 and S103 according to the above embodiments 2 and 3 respectively.

[0124] In one example, to collect the aforementioned state data, the detection module 410 may include a tension sensor, a vibration sensor, a temperature sensor, and an imaging device, which are used to acquire the tension, vibration frequency, temperature, diameter, and number of surface scratches of the cutting line, respectively.

[0125] For example, tension sensors can be mounted on the end faces of the shafts of the front and rear guide rollers of the slicer, and vibration sensors can be fixed to the top surface of the mounting base of the tensioning mechanism of the slicer. Temperature sensors can be fixed to the side wall of the working chamber of the slicer, and imaging devices can be mounted on the frame of the slicer.

[0126] This invention constructs a multi-dimensional sensing system by simultaneously monitoring multiple physical parameters of the cutting wire, including tension, vibration frequency, temperature, cutting speed, diameter, and surface scratches. These parameters exhibit a synergistic evolution pattern during the cutting wire wear process. For example, abnormal fluctuations in tension are often accompanied by changes in the vibration spectrum, while increases in temperature are intrinsically correlated with cutting speed and the accumulation of surface scratches. By comprehensively analyzing these interrelated dynamic data, the data processing module can capture early abnormal features that cannot be reflected by a single indicator, thereby identifying the gradual evolution process from normal state to abnormal warning and even emergency failure. This multi-parameter fusion-based evaluation mechanism enables the system to issue early warnings at an early stage before significant degradation or breakage of the cutting wire performance. Since this invention relies entirely on the analysis of physical behavior and does not involve electrical properties, its application is not limited by the conductivity of the cutting wire material, achieving universal monitoring and early protection for various types of cutting wire conditions.

[0127] In the above embodiments, the descriptions of each embodiment have different focuses. For parts that are not described in detail or recorded in a certain embodiment, please refer to the relevant descriptions of other embodiments.

Claims

1. A photovoltaic slicing machine cutting line status detection system, characterized in that, include: The detection module is used to acquire the status data of the cutting line, wherein the status data includes at least three of the following: tension of the cutting line, vibration frequency, temperature, cutting speed, diameter and number of surface scratches. A data processing module is used to determine whether the cutting line is in a warning state based on the status data. If the cutting line is in an early warning state, the data processing module is further used to determine the operating state of the cutting line based on the state data, wherein the operating state includes: normal, abnormal early warning, and emergency fault. Specifically, the data processing module is used for: Based on the tension, vibration frequency, and diameter of the cutting wire, determine whether the cutting wire is in an early warning state; Alternatively, the tension of the cutting line, the cutting speed, and the number of surface scratches can be used to determine whether the cutting line is in a warning state. Alternatively, the state of the cutting line can be determined based on its tension, diameter, and vibration frequency. Specifically, if the tension of the cutting line is greater than a first preset multiple of a tension threshold, the vibration frequency is greater than a second preset multiple of a frequency threshold, and the diameter change rate is greater than a diameter change ratio threshold, then the cutting line is in the warning state; if the correlation coefficient between the tension of the cutting line and the cutting speed is less than a correlation threshold, and the number of surface scratches is greater than a maximum scratch number threshold, then the cutting line is in the warning state; if the tension of the cutting line is less than a third preset multiple of a tension threshold, or the diameter change rate is greater than a fourth preset multiple of a diameter change ratio threshold, and the high-frequency vibration component is greater than a high-frequency component threshold, then the cutting line is in the warning state.

2. The system according to claim 1, characterized in that, The diameter is determined based on the edge of the cutting line, the gray value of the edge of the cutting line in the image of the cutting line is less than or equal to half of the center gray value; the area where the surface scratch is located includes at least N consecutive pixels in the image of the cutting line where the gray value difference between adjacent pixels is greater than or equal to a gray value difference threshold, where N is a positive integer.

3. The system according to claim 1, characterized in that, The data processing module is also specifically used for: Based on the state data thresholds, a feature score is calculated for each state data, wherein the state data thresholds include at least three of the following: tension threshold, frequency threshold, temperature threshold, diameter change ratio threshold, and maximum number of scratches threshold. Based on the feature scores, the correlation degree between each pair of state data is calculated; Based on the correlation degree, a real-time weight for each state data is determined, wherein the sum of the real-time weights is 1; The real-time state score of the cutting line is determined based on the feature score and the real-time weight. The real-time state score is corrected based on the historical trend of the state score of the cutting line to obtain the corrected real-time state score. The operating status of the cutting line is determined based on the warning interval in which the corrected real-time status score is located, wherein the warning interval and the type of operating status correspond one-to-one, and no two warning intervals overlap.

4. The system according to claim 3, characterized in that, The real-time weights satisfy the following formula. in: in, For the first Real-time weights of various state data The first of the correlation matrix The correlation matrix is ​​composed of the feature value . State data and the first correlation of state data constitute, This represents the total number of state data types.

5. The system according to claim 3, characterized in that, The real-time status score satisfies the following formula: in, The real-time status score of the cutting line is given. This represents the total number of state data types. This is a dispersion adjustment factor that controls the influence of feature score dispersion.

6. The system according to claim 3, characterized in that, The corrected real-time state score satisfies the following formula: in, This is the corrected real-time status score. , These are the mean and standard deviation of the historical state scores, respectively. For trend weight parameters, For integration weight parameters, The average slope of the real-time state score in the previous period. This represents the total number of sampling points in one sampling cycle.

7. The system according to claim 1, characterized in that, The detection module includes a tension sensor, a vibration sensor, a temperature sensor, and an imaging device, which are used to acquire the tension, vibration frequency, temperature, and image of the cutting line, respectively. The cutting speed is obtained from the encoder of the spindle motor of the slicer. The tension sensor is disposed on the end face of the shaft of the front and rear guide wheels of the slicer, the vibration sensor is fixed on the top surface of the fixed seat of the tensioning mechanism of the slicer, the temperature sensor is fixed on the side wall of the working chamber of the slicer, and the imaging device is mounted on the frame beam of the slicer.

8. A method for detecting the cutting line status of a photovoltaic slicing machine, characterized in that, include: Acquire the status data of the cutting line, wherein the status data includes at least three of the following: tension of the cutting line, vibration frequency, temperature, cutting speed, and image; Based on the status data, determine whether the cutting line is in a warning state; If the cutting line is in an early warning state, the operating state of the cutting line is determined based on the state data, wherein the operating state includes: normal, abnormal warning, and emergency fault. The step of determining whether the cutting line is in a warning state based on the status data includes: Based on the tension, vibration frequency, and diameter of the cutting wire, determine whether the cutting wire is in an early warning state; Alternatively, the tension of the cutting line, the cutting speed, and the number of surface scratches can be used to determine whether the cutting line is in a warning state. Alternatively, the state of the cutting line can be determined based on its tension, diameter, and vibration frequency. Specifically, if the tension of the cutting line is greater than a first preset multiple of a tension threshold, the vibration frequency is greater than a second preset multiple of a frequency threshold, and the diameter change rate is greater than a diameter change ratio threshold, then the cutting line is in the warning state; if the correlation coefficient between the tension of the cutting line and the cutting speed is less than a correlation threshold, and the number of surface scratches is greater than a maximum scratch number threshold, then the cutting line is in the warning state; if the tension of the cutting line is less than a third preset multiple of a tension threshold, or the diameter change rate is greater than a fourth preset multiple of a diameter change ratio threshold, and the high-frequency vibration component is greater than a high-frequency component threshold, then the cutting line is in the warning state.

Images