Data analysis method, device and computer equipment for feed production equipment

Abstract

The application relates to a data analysis method and device of a feed production equipment, computer equipment and a storage medium. The method comprises the following steps: obtaining production operation data of the feed production equipment; when the feed production equipment is a granulator, the operation state of the granulator is classified according to the main machine current, steam flow, output and side communication signal in the production operation data to obtain a classification result; when the feed production equipment is an extruder, the operation state of the extruder is classified according to the main machine current, steam flow and feeding amount in the production operation data to obtain a classification result; and in response to an abnormality analysis operation, the granulator or the extruder is subjected to abnormality analysis based on the classification result. According to the method, corresponding production operation data can be selected according to different feed production equipment to obtain classification results corresponding to different equipment, so that the abnormal state of the feed production equipment can be better determined in response to the abnormality analysis operation, and the production efficiency is improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of equipment analysis, in particular to a data analysis method and device for a feed production equipment, a computer equipment, a storage medium and a computer program product. BACKGROUND

[0002] The existing raw feed products such as straw, grass, meat and eggs can be processed into pellet feed or expanded feed, which not only can be sterilized but also is easy to digest and absorb, and significantly improves the feed conversion rate. Therefore, the pellet feed has broad application prospects. In the production process of the feed, various forages, concentrates and premixes required for breeding are proportioned and processed, which can meet the nutritional needs of livestock at different growth stages.

[0003] With the update of the feed production equipment and the increase of the feed production capacity, the abnormal state of the feed production equipment is more and more, thus leading to low production efficiency. SUMMARY

[0004] Therefore, it is necessary to provide a data analysis method and device for a feed production equipment, a computer equipment, a computer readable storage medium and a computer program product, which can improve the production efficiency.

[0005] In a first aspect, the present application provides a data analysis method for a feed production equipment, the method comprising:

[0006] obtaining production running data of the feed production equipment;

[0007] when the feed production equipment is a pellet mill, classifying the running state of the pellet mill according to the main engine current, steam flow, output and side signal in the production running data to obtain a classification result;

[0008] when the feed production equipment is an expander, classifying the running state of the expander according to the main engine current, steam flow and feeding amount in the production running data to obtain a classification result;

[0009] in response to an abnormal analysis operation, performing abnormal analysis on the pellet mill or the expander based on the classification result.

[0010] In one embodiment, the production running data is obtained in real time at different time points; and the obtaining of the production running data of the feed production equipment comprises:

[0011] determining a plurality of time points corresponding to the production running data;

[0012] When a target time point in the plurality of time points is missing production operation data, production operation data corresponding to an adjacent time point before the target time point is filled into a data field corresponding to the target time point, to obtain production operation data of the target time point.

[0013] In one of the embodiments, the classification result includes a stable production state or a non-stable production state; and the operation state of the granulator is classified according to the host current, steam flow, output, and bypass signal in the production operation data, to obtain a classification result, including:

[0014] The host current, steam flow, output, and bypass signal in the production operation data are filtered to obtain filtered production operation data;

[0015] When the host current, output, and bypass signal in the filtered production operation data meet a first preset condition, the steam flow in the filtered production operation data is divided into a plurality of window intervals;

[0016] When the gradient of the plurality of window intervals does not exceed a preset gradient, it is determined that the granulator is in a stable production state;

[0017] When the gradient of the plurality of window intervals exceeds the preset gradient, it is determined that the granulator is in a non-stable production state.

[0018] In one of the embodiments, the operation state of the puffing machine is classified according to the host current, steam flow, and feeding amount in the production operation data, to obtain a classification result, including:

[0019] The host current, steam flow, and feeding amount in the production operation data are filtered to obtain filtered production operation data;

[0020] When the host current and feeding amount in the filtered production operation data meet a second preset condition, the steam flow in the filtered production operation data is divided into a plurality of window intervals;

[0021] When the gradient of the plurality of window intervals does not exceed a preset gradient, it is determined that the puffing machine is in a stable production state;

[0022] When the gradient of the plurality of window intervals exceeds the preset gradient, it is determined that the puffing machine is in a non-stable production state.

[0023] In one of the embodiments, the method further includes:

[0024] After determining that the pelletizer is in a stable production state or the expander is in a stable production state, if the main machine current suddenly changes and decreases to below a preset stable production threshold within a preset time period after the sudden change, and the steam flow also changes during the change of the main machine current, the state of the pelletizer or the expander is updated to another state.

[0025] In one of the embodiments, the method further comprises:

[0026] In response to a production recommendation operation, determining a corresponding recommendation system according to the production operation data and the corresponding device state;

[0027] Performing data processing on the production operation data through the recommendation system to obtain production parameters of the expander or the pelletizer;

[0028] Recommending the production parameters to instruct the expander or the pelletizer to produce according to the production parameters.

[0029] In one of the embodiments, when the feed production equipment is a pelletizer, the classification result includes a main machine start state, a stable production state, a non-stable production state, a main machine stop state, a conditioning waste state, a machine washing state, a standby state, or another state.

[0030] When the feed production equipment is an expander, the classification result includes a non-stable production state, a stable production state, a main machine stop state, a conditioning waste state, a discharge state, a machine washing state, a standby state, and another state.

[0031] In a second aspect, the application further provides a data analysis device of a feed production equipment. The device comprises:

[0032] An operation data acquisition module for acquiring production operation data of a feed production equipment;

[0033] A pelletizer operation data determination module for, when the feed production equipment is a pelletizer, classifying an operation state of the pelletizer according to main machine current, steam flow, output, and a side signal in the production operation data to obtain a classification result;

[0034] An expander data determination module for, when the feed production equipment is an expander, classifying an operation state of the expander according to main machine current, steam flow, and feeding amount in the production operation data to obtain a classification result;

[0035] An equipment classification module for, in response to an abnormality analysis operation, performing abnormality analysis on the pelletizer or the expander based on the classification result.

[0036] In a third aspect, the present application provides a computer device. The computer device comprises a memory and a processor, the memory stores a computer program, and the processor implements the steps of the data analysis method of the feed production equipment when executing the computer program.

[0037] In a fourth aspect, the present application provides a computer readable storage medium. The computer readable storage medium stores a computer program, and the computer program implements the steps of the data analysis method of the feed production equipment when executed by a processor.

[0038] In a fifth aspect, the present application provides a computer program product. The computer program product comprises a computer program, and the computer program implements the steps of the data analysis method of the feed production equipment when executed by a processor.

[0039] The data analysis method, device, computer device, storage medium and computer program product of the feed production equipment are used to obtain production running data of the feed production equipment; when the feed production equipment is a pellet mill, the running state of the pellet mill is classified according to the main motor current, steam flow, output and side communication signal in the production running data to obtain a classification result; when the feed production equipment is an expander, the running state of the expander is classified according to the main motor current, steam flow and feeding amount in the production running data to obtain a classification result; thus, the production running data is selected according to different feed production equipment for classification to obtain a classification result corresponding to different equipment, and when responding to an abnormal analysis operation, the pellet mill or the expander is analyzed based on the classification result to accurately determine the abnormal state of the feed production equipment, so that the production efficiency is improved and the energy consumption is reduced. BRIEF DESCRIPTION OF DRAWINGS

[0040] Figure 1 The application environment diagram of the data analysis method of the feed production equipment in an embodiment;

[0041] Figure 2 The flowchart of the data analysis method of the feed production equipment in an embodiment;

[0042] Figure 3 The production running data diagram of the pellet mill in a production state in an embodiment;

[0043] Figure 4 The production running data diagram of the pellet mill in a production state in an embodiment; Figure 3 The production running data diagram of the pellet mill in a production state in an embodiment;

[0044] Figure 5 The production running data diagram of the pellet mill in a production state in an embodiment; Figure 3 The production running data diagram of the pellet mill in a production state in an embodiment;

[0045] Figure 6 Production run data for a pellet mill in a production state for one embodiment;

[0046] Figure 7 Production run data for a pellet mill in a production state for one embodiment;

[0047] Figure 8 Production run data for a pellet mill in a production state for one embodiment;

[0048] Figure 9 Production run data for a pellet mill in a production state for one embodiment;

[0049] Figure 10 Production run data for a pellet mill in a production state for one embodiment;

[0050] Figure 11 Production run data for a pellet mill in a production state for one embodiment;

[0051] Figure 12 Production run data for a pellet mill in a production state for one embodiment;

[0052] Figure 13 Production run data for a pellet mill in a production state for one embodiment;

[0053] Figure 14 Production run data for a pellet mill in a production state for one embodiment;

[0054] Figure 15 Production run data for a pellet mill in a production state for one embodiment;

[0055] Figure 16 Production run data for a pellet mill in a production state for one embodiment;

[0056] Figure 17 Production run data for a pellet mill in a production state for one embodiment;

[0057] Figure 18 Production run data for a pellet mill in a production state for one embodiment;

[0058] Figure 19 Production run data for a pellet mill in a production state for one embodiment;

[0059] Figure 20Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0060] Figure 21 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0061] Figure 22 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0062] Figure 23 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0063] Figure 24 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0064] Figure 25 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0065] Figure 26 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0066] Figure 27 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0067] Figure 28 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0068] Figure 29 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0069] Figure 30 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0070] Figure 31 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0071] Figure 32 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0072] Figure 33 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment;

[0073] Figure 34 Figure 6 is a schematic diagram of production run data for the extruder in a conditioning waste material state for another embodiment; DETAILED DESCRIPTION

[0074] In order to make the purposes, technical solutions and advantages of the present application clearer, further detailed description will be given below in combination with the drawings and examples. It should be understood that the specific examples described herein are only used to explain the present application and not to limit the present application. In the following description, the meaning of "A and / or B" is "at least one of A and B".

[0075] The data analysis method of the feed production equipment provided by the embodiments of the present application can be applied to the application environment as shown in Figure 1 . The terminal 102 communicates with the server 104 through the network. The data storage system can store the data required to be processed by the server 104. The data storage system can be integrated on the server 104, or placed on the cloud or other network servers. The terminal 102 acquires production running data of the feed production equipment; when the feed production equipment is a pellet mill, the running state of the pellet mill is classified according to the main machine current, steam flow, output and side communication signal in the production running data, and a classification result is obtained; when the feed production equipment is an expander, the running state of the expander is classified according to the main machine current, steam flow and feeding amount in the production running data, and a classification result is obtained; and in response to an abnormality analysis operation, the pellet mill or the expander is analyzed based on the classification result.

[0076] The terminal 102 can be, but is not limited to, various personal computers, notebook computers, smart phones, tablet computers, Internet of Things devices and portable wearable devices. The Internet of Things device can be a smart speaker, a smart television, a smart air conditioner, a smart vehicle-mounted device, etc. The portable wearable device can be a smart watch, a smart bracelet, a head-mounted device, etc. The server 104 can be implemented by an independent server or a server cluster composed of multiple servers. The scheme provided by the embodiments of the present application can be implemented by the terminal 102; or the terminal 102 and the server 104 can be cooperatively implemented, for example, the terminal 102 can provide certain information to the server 104, so that the server 104 performs a calculation process related to the bill display, and the server 104 feeds back the calculation result to the terminal 102, and then the terminal 102 implements.

[0077] In one embodiment, as shown in Figure 2 , a data analysis method of a feed production equipment is provided. Taking the terminal 102 in Figure 1 as an example, the method includes the following steps:

[0078] Step 202, acquiring production running data of the feed production equipment.

[0079] The feed production equipment is used for processing forage, concentrate and mixed agent, and is various in type. Each type of equipment has different production running data, and each equipment determines the required running state according to different production running data, so as to more accurately determine the respective production running data.

[0080] In one embodiment, the production running data is acquired in real time at different time points; the production running data of the feed production equipment is acquired, including: determining a plurality of time points corresponding to the production running data; when a target time point in the plurality of time points lacks production running data, filling the production running data corresponding to the adjacent time point before the target time point into the data field corresponding to the target time point to obtain the production running data of the target time point.

[0081] Therefore, the data field corresponding to the target time point is completed by the acquired production running data, which can transmit the corresponding production running data at the time point of production running data change, without acquiring the corresponding data at each time point, reducing the data acquisition frequency and improving the data transmission efficiency. In addition, even if data loss occurs, it can be completed to ensure the state analysis effect.

[0082] Optionally, in order to determine the equipment state well, the steam flow in the production running data needs to be denoised, and the steam flow less than the corresponding denoising threshold is determined as 0; for example: when the denoising threshold is 5, the steam flow less than 5 is 0. This is because the steam data has many burrs. In addition, under normal circumstances, after shutdown, the steam value should be zero.

[0083] Step 204, when the feed production equipment is a pelletizer, the running state of the pelletizer is classified according to the main engine current, steam flow, output and bypass signal in the production running data to obtain a classification result.

[0084] The pelletizer is a production equipment for mixing and stirring materials such as forage, beans, meat and eggs with modulating agents to produce granular feed. In the production running data corresponding to the pelletizer, the main engine current is the current for controlling the pelletizer to be in the state of starting, producing, washing and waste treatment; the steam flow is the steam flow added to the pelletizer; the output is the amount of granular feed produced by the pelletizer or the amount of waste discharged; and the bypass signal is a signal for controlling the opening of the bypass door of the pelletizer to discharge from the bypass door.

[0085] In one embodiment, the classification result includes a stable production state or a non-stable production state; the operation state of the granulator is classified according to the host current, steam flow, output and bypass signal in the production operation data to obtain the classification result, including: filtering the host current, steam flow, output and bypass signal in the production operation data to obtain filtered production operation data; when the host current, output and bypass signal in the filtered production operation data meet the first preset condition, the steam flow in the filtered production operation data is divided into a plurality of window intervals; when the gradient of the plurality of window intervals does not exceed the preset gradient, it is determined that the granulator is in a stable production state; when the gradient of the plurality of window intervals exceeds the preset gradient, it is determined that the granulator is in a non-stable production state.

[0086] Optionally, the filtering method can be a savgol_filter filtering method, which is a filtering method based on local polynomial least squares fitting in time domain. The filter can ensure that the shape and width of the signal remain unchanged while filtering out noise. Its operation on the signal is to perform polynomial fitting on the data in the window length in the time domain. From the frequency domain, this fitting is used to pass low-frequency data and filter out high-frequency data. It relies on a weighted average algorithm of a moving window and least squares fitting of a given high-order polynomial in a sliding window to filter.

[0087] The savgol_filter filter can be inherited from the scipy library, and the formula for configuring the filter is: scipy.signal.savgol_filter(x, window_length, polyorder), where x is the data to be fitted, window_length is the window size, and polyorder is the order of the polynomial to be fitted. The larger the window_length, the more obvious the smoothing effect, and the smaller the more close to the original curve. The smaller the polyorder, the more obvious the smoothing effect; the larger the polyorder, the more close to the original curve. After filtering and adjusting the steam value of the granulator, it is found that the more suitable window_length=401 and polyorder=3.

[0088] Further, after filtering, if the host current value of the filtered production operation data is greater than 0, the steam value is greater than 0, the output is greater than 0, and the bypass signal is equal to 0, it is considered to meet the first preset condition, and then the steam flow in the filtered production operation data is divided into a plurality of window intervals. When calculating the window interval gradient, the steam flow data at each time point in each window interval will be down-sampled according to the sampling rate to calculate the window interval gradient.

[0089] After calculating the window interval gradient, when the gradient of multiple window intervals does not exceed the preset gradient, it is determined that the pelletizer is in a stable production state; when the gradient of multiple window intervals exceeds the preset gradient, it is determined that the pelletizer is in a non-stable production state. Thus, whether the pelletizer is in a stable running state is further subdivided.

[0090] Specifically, data of a window region is taken out from the steam flow, the interval of the window region is [0, window], the maximum value of the window region is taken out, and its subscript is recorded, denoted as i. If the gradient from i to i+window does not exceed the gradient threshold gradient_threshold, it is indicated that the data of [i, i+window] is relatively stable; if it exceeds, the window is moved, the step is step, and the window interval is [step, window+step]. If the gradient of the continuous n windows does not exceed the gradient threshold, it is indicated that the steam data has reached a stable value. The time point of the non-stable production state is [start_index, i], the world point of the stable production state is [i, end_index], wherein i is the subscript corresponding to the maximum value of the first window of the continuous n windows, start_index and end_index are the start point and the end point of Production respectively. In addition, in the down-sampling of the window, one digit is taken out from each x (0.1*window) to reconstitute the data, so as to reduce the total amount of data for gradient calculation and improve the calculation efficiency. For example, the window interval window is 350; the window step step is 0.2, the gradient threshold gradient_threshold is 4.5, and the number of continuous multiple windows n is 8.

[0091] Step 206, when the feed production equipment is an expander, the running state of the expander is classified according to the main machine current, steam flow and feeding amount in the production running data, and a classification result is obtained.

[0092] The expander is a feed production equipment for mixing, extruding and pressure cooking materials such as forage, beans, meat and eggs with a preparation agent. The main machine current, steam flow and feeding amount are used for state analysis; wherein the main machine current is the current for controlling the expander to be in a start state, a production state, a machine washing state and a waste treatment state; the steam flow is the steam flow added to the expander; and the feeding amount is the amount of material added to the expander.

[0093] In one embodiment, the running state of the extruder is classified according to the host current, steam flow and feeding amount in the production running data, and a classification result is obtained, including: filtering the host current, steam flow and feeding amount in the production running data to obtain filtered production running data; when the host current and feeding amount in the filtered production running data satisfy a second preset condition, the steam flow in the filtered production running data is divided into a plurality of window intervals; when the gradient of the plurality of window intervals does not exceed a preset gradient, it is determined that the extruder is in a stable production state; and when the gradient of the plurality of window intervals exceeds the preset gradient, it is determined that the extruder is in a non-stable production state.

[0094] Optionally, the second preset condition is used to represent that the extruder is in a production state, and the filtering method and the determination method of whether the production is stable for the extruder and the pelletizer can be the same, and thus are not described in detail. The attribute parameters corresponding to the extruder can also be set as: the window interval window is 58; the window step length step is 0.39; and the gradient threshold gradient_threshold is 17.

[0095] In step 208, the pelletizer or the extruder is analyzed abnormally based on the classification result in response to the abnormal analysis operation.

[0096] Specifically, the abnormal production state of the pelletizer is counted and analyzed according to the production history data. For example, the pelletizer may be blocked during production, which may be caused by the need to replace the ring die or too high moisture of the material or slipping of the pressure roller. At this time, the reasons for the blockage can be analyzed according to the ring die usage time or the moisture of the material, etc.

[0097] Alternatively, the abnormal production state of the extruder is counted and analyzed according to the production history data. For example, the extruder may be blocked due to insufficient material curing degree during production, and the reason for the insufficient material curing degree may be caused by low steam volume, etc.

[0098] In the above data analysis method of the feed production equipment, the production running data of the feed production equipment is obtained; when the feed production equipment is a pelletizer, the running state of the pelletizer is classified according to the host current, steam flow, output and side signal in the production running data, and a classification result is obtained; when the feed production equipment is an extruder, the running state of the extruder is classified according to the host current, steam flow and feeding amount in the production running data, and a classification result is obtained. Thus, according to different feed production equipment, the corresponding production running data is selected, and the corresponding feed production equipment is classified according to the selected production running data, to obtain the classification result corresponding to different equipment. When responding to the abnormal analysis operation, the pelletizer or the extruder is analyzed abnormally based on the classification result. The abnormal state of the feed production equipment can be better solved, so that the production efficiency is improved and the energy consumption is reduced.

[0099] In one embodiment, the method further comprises: after determining that the pellet mill is in the stable production state or the expander is in the stable production state, if the main machine current suddenly changes and decreases to below the preset stable production threshold within a preset time period after the sudden change, and the steam flow also changes during the change of the main machine current, updating the state of the pellet mill or the expander to the other state. Thus, the specific state in the production state is ruled out to more stably ensure the state division of the feed production equipment and provide a more real label value for the online data classification method such as a supervised learning algorithm.

[0100] In one embodiment, the method further comprises: in response to the production recommendation operation, determining a corresponding recommendation system according to the production running data and the corresponding device state; performing data processing on the production running data through the recommendation system to obtain production parameters of the expander or the pellet mill; and recommending the production parameters to instruct the expander or the pellet mill to produce according to the production parameters. Thus, a recommendation system for different formulations is established according to the production history data and the corresponding device state, and the system can recommend the optimal production parameters according to the historical data to improve the production efficiency and reduce the use requirements of personnel for equipment operation.

[0101] In one embodiment, the state of the pellet mill includes a non-stable production state, a stable production state, a main machine stop state, a conditioning waste state, a discharge state, a machine washing state, a standby state, and other states; when the feed production equipment is an expander, the classification result includes: a non-stable production state, a stable production state, a main machine stop state, a conditioning waste state, a discharge state, a machine washing state, a standby state, and other states. The non-stable production state and the stable production state both belong to the production state. When the production state is refined into the non-stable production state and the stable production state, the states of the pellet mill and the expander correspond to 8 states respectively, and the 8 states can be marked by corresponding labels to facilitate machine learning such as supervised learning, to better estimate and analyze abnormalities, and to provide better production parameters. The main machine start state can also be referred to as the main machine on state, and the main machine stop state can also be referred to as the main machine off state.

[0102] Specifically, under the first preset condition, the feed production equipment is a pellet mill, and the pellet mill is in a production state production, whose interval is Figure 3 the region between the two marked endpoints in Figure 3 , the two endpoints in Figure 4 , Figure 5 are shown in sequence; wherein the main machine current value of the pellet mill is greater than 0, the steam value is greater than 0, the output is greater than 0, and the side signal is equal to 0.

[0103] Further, for the labels of the host startup state Startup, the host shutting down state Shutting_down, and the host washing state Washing, the condition is that the host current is greater than 0, the output is equal to 0, and the following flags appear:

[0104] In the startup state stage, as shown in Figure 6 , the interval outside the left current value is equal to 0, and the right current is greater than 0.

[0105] In the shutting down state stage, as shown in Figure 7 , the interval outside the left current value is greater than 0, and the right current is equal to 0.

[0106] In the washing state stage, as shown in Figure 8 , the interval outside the left and right current is greater than 0; or as shown in Figure 9 , the interval outside the left and right current is equal to 0.

[0107] In an embodiment, the feed production device is a pellet mill, and the pellet mill is in the conditioning waste state, which can be as shown in Figure 10 , Figure 11 or Figure 12 : In the marked area in Figure 10 , the host current is greater than 0, the steam value is equal to 0, the output is greater than 0, and the side signal is equal to 0; in the marked area in Figure 11 , the output is greater than 0, and the side signal is equal to 1; in the two areas marked in Figure 12 , the production state duration is less than the corresponding threshold value (for example: 100s), and the interval before and after the interval is the conditioning waste state, and this stage is judged as the conditioning waste state.

[0108] In an embodiment, the feed production device is a pellet mill, and the pellet mill is in the standby state, the host current value is equal to 0, the output is equal to 0, and the steam value is equal to 0, as shown in Figure 13 .

[0109] In an embodiment, the feed production device is a pellet mill, when the pellet mill has met the first preset condition, the current suddenly rises and then quickly drops below the value during normal stable production, and the steam also changes, then this data cannot be classified as a stable production state, and this period is temporarily classified as other states, at this time, the host current value is equal to 0, the output is equal to 0, and the steam value is equal to 0, as shown in Figure 14 .

[0110] In an embodiment, when the feed production device is a pellet mill, the data before filtering of the production running data is as shown in Figure 15 , and the filtered production running data after filtering is as shown in Figure 16 .

[0111] In one embodiment, the feed production equipment is an expander, and the expander is in a production state when it is in a second preset condition. The second preset condition can be any one of the following three groups of conditions: as shown in Figure 17 , the host current value is greater than 0, the steam flow value is greater than 0, and the feeding amount is greater than 0; as shown in Figure 18 , the host current value is greater than 0, the steam value is equal to 0, the feeding amount is greater than 0, and the duration is less than 10s, and the steam values on both sides of the interval are greater than 0; still as shown in Figure 18 , the host current value is greater than 0, the steam value is greater than 0, the feeding amount is equal to 0, and the duration is less than 100s, and the steam value, the current value, and the feeding amount on both sides of the interval are greater than 0.

[0112] In one embodiment, the feed production equipment is an expander, and the expander is in a conditioning waste state, and the condition can be shown in the area marked in Figure 19 , Figure 20 or Figure 21 . Figure 19 , the host current value is equal to 0, the steam value is greater than 0, the feeding amount is greater than 0, the current on the left side outside the interval is equal to 0, and the current on the right side is greater than 0; Figure 20 , the host current value is equal to 0, the steam value is equal to 0, the feeding amount is greater than 0, if the duration is short, for example, less than 5s, and the steam values on both sides outside the interval are greater than 0; Figure 21 , the host current value is greater than 0 but small, the steam value is greater than 0, and the feeding amount is greater than 0. There is a case that the host current is not completely turned off, and there is a small current, which can be ignored at this time.

[0113] In one embodiment, when the feed production equipment is an expander, the data before filtering of the production running data is as shown in Figure 22 , and the category production running data after listing is as shown in Figure 23 .

[0114] In one embodiment, the feed production equipment is an expander, and the expander is in a host washing state, the host current value is greater than 0, the feeding amount is equal to 0, and the steam flow values on both sides outside the interval are 0, which is as shown in Figure 24 .

[0115] In one embodiment, the feed production equipment is an expander, and the expander is in a host shutdown state, and the shutdown state is as shown in the interval marked in Figure 25 , Figure 26 or Figure 27 . Figure 24 , the host current value is greater than 0, the steam value is equal to 0, the feeding amount is equal to 0, and the steam value on the left side outside the interval is greater than 0; Figure 26 , the host current value is greater than 0, the steam value is greater than 0, and the feeding amount is equal to 0; Figure 27In the interval marked in the figure, the host current value is greater than 0, the steam flow value is equal to 0, and the feeding amount is greater than 0.

[0116] In one embodiment, the feed production device is an expander, the expander is in the standby state, the host current value is equal to 0, the steam value is equal to 0, and the feeding amount is equal to 0, which is as shown in the figure. Figure 28

[0117] In one embodiment, the feed production device is an expander, the expander is in the discharging state, the discharging state is as shown in the figure. Figure 29 or Figure 30 the interval marked in the figure; Figure 29 the interval in the figure, the host current value is equal to 0, the steam value is equal to 0, the feeding amount is greater than 0, and the gradient of the cumulative yield value of the segment is not 0; Figure 30 the interval in the figure, the host current value is greater than 0, the steam value is equal to 0, and the feeding amount is greater than 0.

[0118] In one embodiment, the feed production device is an expander, the start-up time should be greater than the shut-down time, when the shut-down time is long, the region corresponding to the shut-down state needs to be cropped, and the region marked in the figure is the corresponding cropped region, when analyzing the current of the region, it is found that the current of a certain point will decrease and then remain unchanged for a certain period of time, and the turning point is the timely cropped point; after cropping the data, the corresponding shut-down interval is cropped, which is as shown in the figure. Figure 31 Figure 32 In addition, all the flags of the host working states that have been classified are listed, and after ascending arrangement, if a certain region does not belong to any of the above flags, other flags are defined as other states.

[0119] It should be understood that although each step in the flowchart involved in each embodiment as described above is displayed in sequence according to the arrow indication, these steps are not necessarily executed in sequence according to the arrow indication. Unless explicitly stated in this article, the execution of these steps has no strict sequence limitation, and these steps can be executed in other orders. Moreover, at least part of the steps in the flowchart involved in each embodiment as described above can include multiple steps or stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily sequential, but can be alternately executed with at least part of other steps or steps or stages in other steps.

[0120] ​​Based on the same inventive concept, the embodiments of the present application also provide a data analysis device of the feed production equipment for implementing the data analysis method of the feed production equipment. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme described in the above method, so the specific limitations in one or more data analysis device embodiments of the feed production equipment provided below can refer to the limitations of the data analysis method of the feed production equipment in the above, which will not be described here again.

[0121] In one embodiment, as shown in Figure 33 A data analysis device of a feed production equipment is provided, comprising: a running data acquisition module 3302, a pellet mill running data determination module 3304, an expander data determination module 3306, and an equipment classification module 3308, wherein:

[0122] The running data acquisition module 3302 is configured to acquire production running data of the feed production equipment.

[0123] The pellet mill running data determination module 3304 is configured to, when the feed production equipment is a pellet mill, classify a running state of the pellet mill according to main machine current, steam flow, output, and bypass signal in the production running data to obtain a classification result.

[0124] The expander data determination module 3306 is configured to, when the feed production equipment is an expander, classify a running state of the expander according to main machine current, steam flow, and feeding amount in the production running data to obtain a classification result.

[0125] The equipment classification module 3308 is configured to, in response to an abnormality analysis operation, perform abnormality analysis on the pellet mill or the expander based on the classification result.

[0126] In one embodiment, the production running data is acquired in real time at different time points. The running data acquisition module 3302 comprises:

[0127] A time point determination unit is configured to determine a plurality of time points corresponding to the production running data.

[0128] A missing time supplement unit is configured to, when a target time point in the plurality of time points is missing production running data, fill production running data corresponding to an adjacent time point before the target time point into a data field corresponding to the target time point to obtain production running data of the target time point.

[0129] In one embodiment, the classification result comprises a stable production state or a non-stable production state. The pellet mill running data determination module 3304 comprises:

[0130] The first filtering unit is configured to filter host current, steam flow, output and bypass signals in the production operation data to obtain filtered production operation data.

[0131] The first window determining unit is configured to divide the steam flow in the filtered production operation data into a plurality of window intervals when the host current, output and bypass signals in the filtered production operation data satisfy a first preset condition.

[0132] The first echelon calculating unit is configured to determine that the granulator is in a stable production state when gradients of the plurality of window intervals do not exceed a preset gradient.

[0133] The granulator state determining unit is configured to determine that the granulator is in a non-stable production state when the gradients of the plurality of window intervals exceed the preset gradient.

[0134] In one embodiment, the bulking machine data determining module 3306 comprises:

[0135] The second filtering unit is configured to filter host current, steam flow and feeding amount in the production operation data to obtain filtered production operation data.

[0136] The second window determining unit is configured to divide the steam flow in the filtered production operation data into a plurality of window intervals when the host current and feeding amount in the filtered production operation data satisfy a second preset condition.

[0137] The second echelon calculating unit is configured to determine that the bulking machine is in a stable production state when gradients of the plurality of window intervals do not exceed a preset gradient.

[0138] The bulking machine state determining unit is configured to determine that the bulking machine is in a non-stable production state when the gradients of the plurality of window intervals exceed the preset gradient.

[0139] In one embodiment, the device further comprises a temperature state subdivision module configured to, after determining that the granulator is in a stable production state or the bulking machine is in a stable production state, update the state of the granulator or the bulking machine to another state if the host current suddenly changes and decreases to below a preset stable production threshold in a preset time period after the sudden change, and the steam flow also changes in the process of the change of the host current.

[0140] In one embodiment, the device further comprises a recommendation module, wherein the recommendation module comprises:

[0141] The recommendation system determining unit is configured to determine a corresponding recommendation system according to the production operation data and the corresponding device state in response to a production recommendation operation.

[0142] a running data processing unit configured to process the production running data by the recommendation system to obtain a production parameter of the extruder or the pelletizer;

[0143] a production parameter recommendation unit configured to recommend the production parameter to instruct the extruder or the pelletizer to produce according to the production parameter.

[0144] In one of the embodiments, when the feed production equipment is a pelletizer, the classification result includes: a main machine starting state, a stable production state, a non-stable production state, a main machine stopping state, a conditioning waste state, a machine washing state, a standby state or other states.

[0145] When the feed production equipment is an extruder, the classification result includes: a non-stable production state, a stable production state, a main machine stopping state, a conditioning waste state, a discharging state, a machine washing state, a standby state and other states.

[0146] The above-mentioned various modules in the data analysis device of the feed production equipment can be realized by software, hardware and combinations thereof in whole or in part. The above-mentioned various modules can be embedded in or independent of the processor in the computer device in hardware form, or can be stored in the memory in the computer device in software form, so as to be called and executed by the processor to perform the operations corresponding to the above-mentioned various modules.

[0147] In one embodiment, a computer device can be provided, which can be a terminal, and the internal structure diagram thereof can be as shown in Figure 34 The computer device includes a processor, a memory, a communication interface, a display screen and an input device connected through a system bus. The processor of the computer device is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operating system and the computer program in the non-volatile storage medium to run. The communication interface of the computer device is configured to perform wired or wireless communication with an external terminal. The wireless communication can be achieved by WIFI, mobile cellular network, NFC (near field communication) or other technologies. The computer program is executed by the processor to implement a data analysis method of a feed production equipment. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer overlaid on the display screen, or can be a key, trackball or touchpad arranged on the shell of the computer device, or can be an external keyboard, touchpad or mouse, etc.

[0148] Those skilled in the art can understand that, Figure 34The structure shown in the figure is only a block diagram of part of the structure related to the scheme of the present application, and does not constitute a limitation on the computer device to which the scheme of the present application is applied. The specific computer device can include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0149] In an embodiment, a computer device is also provided, including a memory and a processor, the memory storing a computer program, and the processor implementing the steps in the above method embodiments when executing the computer program.

[0150] In an embodiment, a computer readable storage medium is provided, storing a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0151] In an embodiment, a computer program product is provided, including a computer program, and the computer program implementing the steps in the above method embodiments when executed by a processor.

[0152] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or authorized by all parties.

[0153] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer readable storage medium, and when the computer program is executed, the processes of the above-mentioned embodiments of the methods can be included. Any reference to memory, database or other medium used in the embodiments provided in the present application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical storage, high-density embedded non-volatile memory, resistive memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration but not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The database involved in the embodiments provided in the present application can include at least one of a relational database and a non-relational database. The non-relational database can include a distributed database based on a block chain, etc., without being limited thereto. The processor involved in the embodiments provided in the present application can be a general-purpose processor, a central processing unit, a graphics processing unit, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., without being limited thereto.

[0154] Any combination of the technical features of the above embodiments can be made. In order to make the description simple, all possible combinations of the technical features in the above embodiments are not described, however, as long as the combination of the technical features does not exist, it should be considered as the scope of the present application.

[0155] The above embodiments only express several implementation manners of the present application, and the description is more specific and detailed, but it should not be understood as a limitation on the scope of the patent of the present application. It should be pointed out that for ordinary skilled in the art, without departing from the concept of the present application, a number of modifications and improvements can be made, which are all within the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the appended claims.

Claims

1. A data analysis method of a feed production apparatus, characterized by, The method comprises: acquiring production operation data of a feed production device; when the feed production device is a pelletizer, filtering host current, steam flow, output and bypass signal in the production operation data to obtain filtered production operation data of the pelletizer; when the host current, output and bypass signal in the filtered production operation data of the pelletizer meet a first preset condition, dividing the steam flow in the filtered production operation data of the pelletizer into multiple window intervals of the pelletizer; when the gradient of the multiple window intervals of the pelletizer does not exceed a preset gradient, determining that the pelletizer is in a stable production state; when the gradient of the multiple window intervals of the pelletizer exceeds the preset gradient, determining that the pelletizer is in a non-stable production state; the output of the pelletizer comprises waste discharge amount of the pelletizer; the stable production state or the non-stable production state of the pelletizer belongs to a classification result; when the feed production device is an expander, filtering host current, steam flow and feeding amount in the production operation data to obtain filtered production operation data of the expander; when the host current and feeding amount in the filtered production operation data meet a second preset condition, dividing the steam flow in the filtered production operation data of the expander into multiple window intervals of the expander; when the gradient of the multiple window intervals of the expander does not exceed a preset gradient, determining that the expander is in a stable production state; when the gradient of the multiple window intervals of the expander exceeds the preset gradient, determining that the expander is in a non-stable production state; the stable production state and the non-stable production state belong to a classification result; in response to an abnormality analysis operation, performing abnormality analysis on the pelletizer or the expander based on the classification result.

2. The method of claim 1, wherein, The production operation data is acquired in real time at different time points; the acquiring of the production operation data of the feed production device comprises: determining multiple time points corresponding to the production operation data; when a target time point in the multiple time points lacks production operation data, filling the production operation data corresponding to an adjacent time point before the target time point into a data field corresponding to the target time point to obtain production operation data of the target time point.

3. The method of claim 2, wherein, The filtering of the host current, steam flow, output and bypass signal in the production operation data to obtain the filtered production operation data of the pelletizer comprises: performing weighted average processing on the host current, steam flow, output and bypass signal in a window length in a time domain to obtain weighted average results of polynomials in a sliding window; performing fitting and filtering on the weighted average results of the polynomials based on a least square method for filtering high-frequency data and passing low-frequency data to obtain the filtered production operation data of the pelletizer; The filtering of the host current, steam flow, feeding amount in the production operation data to obtain the filtered production operation data of the expander comprises: The host current, the steam flow, the output and the bypass signal in a window length in a time domain are weighted and averaged to obtain a weighted average result of a polynomial in a sliding window; and the weighted average result of the polynomial is fitted and filtered based on a least square method for filtering high-frequency data and passing low-frequency data to obtain filtered production operation data of the bulking machine.

4. The method of claim 2, wherein, The method further comprises: After determining that the pelletizer is in the stable production state or the bulking machine is in the stable production state, if the host current suddenly changes and decreases to below a preset stable production threshold in a preset time period after the sudden change, and the steam flow also changes during the change of the host current, the state of the pelletizer or the bulking machine is updated to another state.

5. The method according to any one of claims 1 to 4, characterized in that, The method further comprises: In response to a production recommendation operation, a corresponding recommendation system is determined according to the production operation data and the corresponding device state; The production operation data is processed by the recommendation system to obtain production parameters of the bulking machine or the pelletizer; The production parameters are recommended to instruct the bulking machine or the pelletizer to produce according to the production parameters.

6. The method of claim 1, wherein, When the feed production device is a pelletizer, the classification result includes: a host start state, a stable production state, a non-stable production state, a host stop state, a conditioning waste state, a machine washing state, a standby state or another state; When the feed production device is a bulking machine, the classification result includes: a non-stable production state, a stable production state, a host stop state, a conditioning waste state, a discharge state, a machine washing state, a standby state and another state.

7. A data analysis device of a feed production device, the device comprising: an operation data acquisition module configured to acquire production operation data of a feed production device; a pelletizer operation data determination module configured to, when the feed production device is a pelletizer, classify a running state of the pelletizer according to a host current, a steam flow, an output and a bypass signal in the production operation data to obtain a classification result, wherein the output includes an amount of waste discharged by the pelletizer; a bulking machine data determination module configured to, when the feed production device is a bulking machine, classify a running state of the bulking machine according to a host current, a steam flow and a feed amount in the production operation data to obtain a classification result; a device classification module configured to, in response to an abnormality analysis operation, perform abnormality analysis on the pelletizer or the bulking machine based on the classification result; the classification result includes a stable production state or a non-stable production state; the pelletizer operation data determination module comprises: a first filtering unit configured to filter a host current, a steam flow, an output and a bypass signal in the production operation data to obtain filtered production operation data of the pelletizer; a first window determination unit configured to, when a host current, an output and a bypass signal in the filtered production operation data of the pelletizer meet a first preset condition, divide a steam flow in the filtered production operation data of the pelletizer into a plurality of window intervals of the pelletizer; and a second window determination unit configured to, when a host current, an output and a bypass signal in the filtered production operation data of the pelletizer meet a second preset condition, divide a steam flow in the filtered production operation data of the pelletizer into a plurality of window intervals of the pelletizer. The first echelon calculation unit is configured to determine that the pelletizer is in a stable production state when the gradient of the multiple window intervals of the pelletizer does not exceed the preset gradient. The pelletizer state determination unit is configured to determine that the pelletizer is in a non-stable production state when the gradient of the multiple window intervals of the pelletizer exceeds the preset gradient. The puffing machine data determination module comprises: The second filter unit is configured to filter the main engine current, steam flow and feeding amount in the production operation data to obtain filtered production operation data of the puffing machine. The second window determination unit is configured to divide the steam flow in the filtered production operation data of the puffing machine into multiple window intervals of the puffing machine when the main engine current and the feeding amount in the filtered production operation data satisfy a second preset condition. The second echelon calculation unit is configured to determine that the puffing machine is in a stable production state when the gradient of the multiple window intervals of the puffing machine does not exceed the preset gradient. The puffing machine state determination unit is configured to determine that the puffing machine is in a non-stable production state when the gradient of the multiple window intervals of the puffing machine exceeds the preset gradient.

8. The apparatus of claim 7, wherein, The production operation data is obtained in real time at different time points. The time point determination unit is configured to determine multiple time points corresponding to the production operation data. The missing time supplement unit is configured to, when a target time point in the multiple time points is missing production operation data, fill the production operation data corresponding to an adjacent time point before the target time point into a data field corresponding to the target time point to obtain production operation data of the target time point. 9.A computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the computer device is configured to perform the method according to any one of claims 1-8 when the computer program is executed by the processor. The processor executes the computer program to implement the steps of the method of any one of claims 1 to 6.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the steps of the method of any one of claims 1 to 6.

Images