A method and system for temperature and humidity control in a biomass fuel pellet forming machine

Abstract

This application provides a method and system for controlling the temperature and humidity of a biomass fuel pellet forming machine, comprising: judging the material humidity information, the operating load information, the quality information of the formed pellets, and the execution information of the humidification adjustment to identify the difference between the material humidity information and the indirect physical feedback information, and determining the operating status of the material humidity measuring device; when the operating status indicates that the material humidity measuring device has a deviation, adjusting the degree of confidence in the material humidity information to obtain a material humidity adjustment value; inferring the actual moisture content of the material based on the operating load information; and issuing a command to adjust the humidification amount based on the inferred actual moisture content of the material and the material humidity adjustment value. This application can effectively identify the deviation of the material humidity measuring device and achieve precise control of the temperature and humidity of the biomass fuel pellet forming machine.

Description

Technical Field

[0001] This application relates to the field of biomass fuel pellet forming technology, and more specifically, to a method and system for controlling temperature and humidity in a biomass fuel pellet forming machine. Background Technology

[0002] In existing biomass fuel pellet forming machines, the humidity probe at the raw material inlet is susceptible to the effects of a mixture of high-temperature water vapor and dust during production. This causes moist dust to adhere and form a dense layer of dirt. This dirt layer severely hinders effective contact between the probe and the actual material, resulting in consistently low humidity readings and a delayed response. The control system, based on this distorted data, over-humidifies the material, leading to excessively high moisture content. This, in turn, causes a series of problems, including a significant increase in the operating load of the forming machine and a decrease in pellet quality.

[0003] Meanwhile, there is a contradiction between the indirect physical feedback information inside the system (such as the material dryness calculated by the motor load) and the direct humidity measurement data. However, because the direct measurement data is given a higher decision weight, the system has difficulty in effectively identifying and correcting errors, which eventually leads to a vicious cycle and seriously affects production efficiency and product quality. Summary of the Invention

[0004] This application provides a method and system for controlling temperature and humidity in a biomass fuel pellet forming machine to solve at least one of the above-mentioned technical problems.

[0005] To achieve the above objectives, this application adopts the following technical solution:

[0006] In a first aspect, this application discloses a method for controlling temperature and humidity in a biomass fuel pellet forming machine, the method comprising:

[0007] Obtain material humidity information provided by the material humidity measuring device;

[0008] Obtain indirect physical feedback information, which includes the operating load information of the components driving the molding machine, the quality information of the molded particles, and the execution information of humidification adjustment;

[0009] The material humidity information, the operating load information, the quality information of the formed particles, and the execution information of the humidification adjustment are judged to identify the differences between the material humidity information and the indirect physical feedback information, and to determine the operating status of the material humidity measuring device.

[0010] When the operating status indicates that the material humidity measuring device has a deviation, the degree of confidence in the material humidity information is adjusted to obtain the material humidity adjustment value;

[0011] Based on the operating load information, the actual moisture content of the material can be inferred.

[0012] Based on the actual moisture content of the material and the material humidity adjustment value, an instruction is issued to adjust the humidification amount.

[0013] When the operating status indicates that the material humidity measuring device has a deviation, a prompt message is issued for the material humidity measuring device.

[0014] Secondly, this application also discloses a temperature and humidity control system for a biomass fuel pellet forming machine, the system comprising:

[0015] The material humidity information acquisition module is used to acquire material humidity information provided by the material humidity measuring device;

[0016] The indirect physical feedback information acquisition module is used to acquire indirect physical feedback information, which includes the operating load information of the components driving the molding machine, the quality information of the molded particles, and the execution information of humidification adjustment.

[0017] The operation status judgment module is used to judge the material humidity information, the operating load information, the quality information of the formed particles, and the execution information of the humidification adjustment, so as to identify the difference between the material humidity information and the indirect physical feedback information, and determine the operation status of the material humidity measuring device.

[0018] The confidence level adjustment module is used to adjust the confidence level of the material humidity information when the operating status indicates that the material humidity measuring device has a deviation, and to obtain the material humidity adjustment value.

[0019] The actual moisture content inference module is used to infer the actual moisture content of the material based on the operating load information.

[0020] The humidification command issuing module is used to issue commands to adjust the humidification amount based on the material's actual moisture content and humidity adjustment value.

[0021] The prompt message issuing module is used to issue a prompt message for the material humidity measuring device when the operating status indicates that there is a deviation in the material humidity measuring device.

[0022] Compared with the prior art, this application has at least the following beneficial effects:

[0023] This application can ensure that even when there is a sensor deviation, the actual moisture content of the material can be more accurately determined, thereby issuing a more reasonable humidification command and avoiding over-humidification or under-humidification. Attached Figure Description

[0024] Figure 1 A schematic flowchart illustrating a method for controlling temperature and humidity in a biomass fuel pellet forming machine, provided in this application;

[0025] Figure 2 This is a schematic diagram of the temperature and humidity control system for a biomass fuel pellet forming machine provided in this application. Detailed Implementation

[0026] The technical solutions of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments.

[0027] like Figure 1 As shown in the embodiment of this application, a method for controlling the temperature and humidity of a biomass fuel pellet forming machine is proposed, including:

[0028] Obtain material humidity information provided by the material humidity measuring device;

[0029] Obtain indirect physical feedback information, which includes the operating load information of the components driving the molding machine, the quality information of the molded particles, and the execution information of humidification adjustment;

[0030] The system assesses material humidity information, operating load information, granule quality information, and humidification adjustment execution information to identify discrepancies between material humidity information and indirect physical feedback information, and to determine the operating status of the material humidity measuring device.

[0031] When the operating status indicates that the material humidity measuring device has a deviation, the degree of confidence in the material humidity information is adjusted to obtain the material humidity adjustment value;

[0032] Based on the operating load information, infer the actual moisture content of the material;

[0033] Based on the actual moisture content of the material and the material humidity adjustment value, an instruction is issued to adjust the humidification amount.

[0034] When the operating status indicates that the material moisture measuring device has a deviation, a prompt message from the material moisture measuring device will be issued.

[0035] This application, through comprehensive analysis of direct humidity measurement data and various indirect physical feedback information, can effectively identify the operational deviation of the material humidity measurement device, adjust the data acceptance level accordingly, infer the actual moisture content of the material by combining the operating load, and thus issue more accurate humidification instructions and timely prompts, effectively avoiding the erroneous adjustments and production problems caused by sensor distortion in traditional control systems.

[0036] A biomass fuel pellet forming machine is a device that produces pellet fuel from biomass raw materials (such as sawdust and straw) through extrusion and heating. A material moisture measurement device typically refers to a sensor installed at the raw material inlet of the forming machine to monitor the moisture content of the biomass raw materials in real time. Examples include resistive moisture sensors, capacitive moisture sensors, or microwave moisture sensors. The material moisture information is the raw moisture measurement data directly output by this device. Indirect physical feedback information refers to information that indirectly reflects the material state by monitoring other physical quantities during the operation of the forming machine. This information includes the operating load information of the components driving the forming machine (e.g., main motor current, torque, etc.), the quality information of the formed pellets (e.g., pellet density, hardness, crack rate, etc.), and the execution information of humidification regulation (e.g., steam valve opening, steam flow rate, etc.). This information collectively forms the basis for evaluating the operating status of the material moisture measurement device and the actual moisture content of the material.

[0037] The temperature and humidity control method for the biomass fuel pellet mill provided in this application will be further described in detail below:

[0038] First, the material moisture information is acquired from the material moisture measuring device. This information can be an analog signal directly output by the material moisture measuring device, such as a voltage or current signal, or a digital signal after analog-to-digital conversion. For example, the material moisture measuring device can be an infrared moisture sensor installed above the raw material conveyor belt, which continuously emits infrared light and receives reflected light. By analyzing the absorption spectrum of the reflected light, the moisture content of the material surface is inferred, and this moisture content data is output as the material moisture information.

[0039] Indirect physical feedback information includes the operating load information of the components driving the molding machine, the quality information of the molded particles, and the execution information of humidification regulation. Operating load information can be obtained by monitoring parameters such as the current, voltage, power, or torque of the main motor driving the molding machine. For example, current transformers and voltage sensors can be installed in the main motor circuit to collect the motor's operating current and voltage in real time and calculate its operating load. The quality information of the molded particles can be obtained through an online quality inspection system, such as detecting the shape and surface cracks of the particles through a visual recognition system, or measuring the particle density through a density sensor. The execution information of humidification regulation can be obtained from the humidification control unit, such as the opening degree of the steam valve, the steam injection rate, or the humidification duration.

[0040] The system analyzes material humidity information, operating load information, granule quality information, and humidification control execution information to identify discrepancies between material humidity information and indirect physical feedback information, and to determine the operating status of the material humidity measurement device. For example, a multivariate analysis model can be established, and this information can be input into the model for real-time comparison. When the material humidity information shows that the material is too dry, while the operating load information shows that the motor load is continuously increasing and the granule quality is decreasing, and the humidification control execution information shows that the system is continuously increasing the humidification amount, these contradictory signals indicate that the material humidity measurement device may be malfunctioning.

[0041] When the operating status indicates a deviation in the material humidity measurement device, the confidence level of the material humidity information is adjusted to obtain an adjusted material humidity value. For example, a dynamic confidence weight can be assigned to the material humidity information based on the severity of the deviation. When the deviation is small, the confidence weight can be set to 0.8; when the deviation is large, the confidence weight can be reduced to 0.2 or even lower. Then, the original material humidity information is weighted and averaged or merged with this confidence weight to obtain a material humidity adjustment value that more closely approximates the actual situation.

[0042] Based on operating load information, the actual moisture content of the material can be inferred. For example, a mapping model between operating load and material moisture content can be pre-established. When the operating load information shows a continuous increase in motor current, this model can infer that the actual moisture content of the material may be too high, leading to increased extrusion resistance. This mapping model can be trained using historical data or calibrated experimentally.

[0043] Based on the material's actual moisture content and the material's humidity adjustment value, the system issues instructions to adjust the humidification rate. For example, if the inferred actual moisture content indicates that the material is too wet, and the humidity adjustment value also indicates that the material's humidity is too high, the system will issue an instruction to reduce the steam injection rate or stop humidification. Conversely, if both indicate that the material is too dry, the system will issue an instruction to increase the humidification rate.

[0044] When the operating status indicates a deviation in the material moisture measurement device, a prompt message is issued. This prompt message can be displayed on the operator interface, such as "The moisture sensor may be dirty; please check and clean it," or it can be alerted to the operator via an audible and visual alarm. The prompt message may include the type of deviation (e.g., low reading, delayed response) and suggested actions (e.g., cleaning the sensor, calibrating the sensor).

[0045] This application effectively identifies operational deviations in material humidity measuring devices by comprehensively analyzing direct humidity measurement data and various indirect physical feedback information. When a deviation occurs in the material humidity measuring device, the system no longer blindly relies on its output data, but adjusts the level of confidence in that data and infers the actual moisture content of the material by combining it with operating load information. This multi-source information fusion and intelligent judgment mechanism enables the system to more accurately grasp the true humidity status of the material, thereby issuing more precise humidification adjustment commands and avoiding over-humidification or under-humidification caused by sensor distortion in traditional control systems.

[0046] This application introduces an intelligent judgment mechanism for the operating status of material moisture measurement devices and achieves fusion decision-making based on multi-source information. Traditional methods mainly rely on single direct moisture measurement data; when this data is distorted, the system falls into an error loop. This application, however, proactively identifies sensor deviations and dynamically adjusts data acceptance weights by comprehensively analyzing the differences between direct measurement data and indirect physical feedback information. This mechanism allows the system to maintain accurate judgment of the actual material state even when faced with sensor failure or performance degradation, thereby avoiding the risks of decreased production efficiency, deteriorated product quality, and equipment damage caused by sensor distortion. Furthermore, this application can promptly issue prompts to guide operators in maintenance, further improving the system's reliability and intelligence.

[0047] In some embodiments, the steps of judging material humidity information, operating load information, shaped particle quality information, and humidification adjustment execution information to identify the differences between material humidity information and indirect physical feedback information, and to determine the operating status of the material humidity measuring device, include:

[0048] Trend analysis was performed on the continuously collected material humidity information, operating load information, shaped particle quality information, and humidification regulation execution information to extract the rate and cumulative change of material humidity information, operating load information, shaped particle quality information, and humidification regulation execution information.

[0049] Based on the preset association rules, the data is compared to the following: the material moisture information shows a continuous downward trend, the operating load information shows a slow cumulative upward trend, and the shaped particle quality information shows a slow downward trend.

[0050] Determine whether a persistently low trend in material moisture information and a slow, cumulative upward trend in operating load information occur simultaneously.

[0051] Determine whether there is a specific time correlation between the slow cumulative increase trend of operating load information and the slow decrease trend of shaped particle quality information;

[0052] When the material moisture information shows a continuous low trend, the operating load information shows a slow cumulative increase trend, and the shaped particle quality information shows a slow decrease trend, all of which simultaneously meet the preset duration threshold and change range threshold, and there is a preset correlation between the change rate of the operating load information and the change rate of the shaped particle quality information, it is determined that there is a deviation in the operation of the material moisture measurement device.

[0053] Specifically, trend analysis refers to the statistical analysis and pattern recognition of historical data to reveal the patterns of data change over time. By extracting the rate of change and cumulative change, the dynamic changes of various information can be quantified. For example, the rate of change of material humidity information can reflect how quickly sensor readings decrease, while the cumulative change indicates the total degree of deviation from normal values. Similarly, the rate of change and cumulative change of operating load information can reflect changes in the working resistance of the molding machine, while the rate of change and cumulative change of molded particle quality information reflect the stability of product quality. The rate of change and cumulative change of humidification regulation execution information can reflect the efforts made by the system to maintain humidity.

[0054] The preset association rules, established based on empirical data or expert knowledge, describe the specific linkage patterns that should exist between various physical feedback information when a material moisture measurement device malfunctions. For example, if the material moisture measurement device reading is low, but the actual material moisture content has not decreased, the molding machine may increase the humidification rate to maintain pellet quality. Simultaneously, because the actual material moisture content may be high, molding resistance increases, operating load rises, and pellet quality decreases. Therefore, comparing the continuously low trend of material moisture content, the slow cumulative increase trend of operating load, and the slow decrease trend of pellet quality are key patterns for identifying sensor deviation.

[0055] Determining whether these trends occur simultaneously and whether they exhibit a specific temporal correlation is crucial to ensuring that these phenomena are indeed caused by the same reason (i.e., sensor bias) rather than by chance or independent factors. For example, if material moisture information is low, but the operating load and particle mass do not change accordingly, it may not be sensor bias. A specific temporal correlation refers to whether these trends occur synchronously in time or exhibit a predictable lag.

[0056] Preset duration and amplitude thresholds are used to filter out short-lived, insignificant fluctuations, ensuring that only persistent and significant abnormal patterns are identified as sensor deviations. For example, the duration threshold can be set to several minutes or hours, and the amplitude threshold can be set to a percentage or absolute value. A preset correlation between the rate of change of operating load information and the rate of change of shaped particle quality information further enhances the accuracy of the judgment, because when sensor deviation causes a deviation in the actual material moisture content, there is often a close physical coupling between the two. Through these comprehensive judgments, the deviation of the material moisture measurement device can be effectively distinguished from signal fluctuations caused solely by material characteristics (such as raw material batch differences, particle size variations, etc.), avoiding misjudgments.

[0057] This application addresses the potential misjudgment problem in assessing the operational status of material humidity measuring devices by introducing trend analysis and correlation judgment of multi-source information. Specifically, when a material humidity measuring device malfunctions, its output material humidity information deviates from the actual material humidity. This deviation is not isolated but indirectly affects the operating load of the molding machine, the quality of the molded particles, and the humidification adjustments made by the system to maintain humidity through a physical coupling mechanism. For example, if the humidity sensor reading is low, but the actual material humidity is normal or high, the system may incorrectly increase the humidification, leading to over-wetting of the material, which in turn increases molding resistance (increased operating load) and reduces the density or strength of the molded particles (decreased quality). This application captures these interconnected effects by continuously monitoring the dynamic trends of these relevant information and extracting their rate of change and cumulative change. By comparing the continuously low trend of material humidity information, the slow cumulative increase trend of operating load information, and the slow decrease trend of molded particle quality information, and determining whether these trends occur simultaneously and have a specific temporal correlation, a multi-dimensional, mutually corroborating chain of evidence can be formed. Furthermore, by setting duration and amplitude thresholds and considering the correlation between the rate of change of operating load information and the rate of change of shaped particle quality information, this application can effectively filter out interference caused by normal production fluctuations or minor changes in material properties, thereby more accurately identifying the true deviation of the material moisture measurement device. This comprehensive judgment mechanism enables the system to effectively distinguish between sensor malfunctions and signal characteristics caused by changes in the material's own properties, avoiding inappropriate control strategies due to misjudgment.

[0058] Assuming a biomass fuel pellet mill is operating continuously, the system continuously monitors the material moisture information output by the material moisture measurement device, which shows a slow, persistently low trend. Simultaneously, analysis of the operating load information of the components driving the pellet mill reveals a slow, cumulative increase, and the pellet mass information also shows a slow, decreasing trend. The system further analyzes the rate of change and cumulative change of these trends. For example, the material moisture information decreased by 2% in the past 30 minutes, the operating load information increased by 5% in the same period, and the average density of the pellets decreased by 1%. The system compares these trends with preset correlation rules and finds that these phenomena conform to the typical pattern when the material moisture measurement device has a deviation. Furthermore, the system determines that these low, increasing, and decreasing trends occur simultaneously, and that there is a preset temporal correlation between the increasing trend of the operating load information and the decreasing trend of the pellet mass information (e.g., approximately 5 minutes after the operating load increases, the pellet mass begins to decrease). When the duration (e.g., exceeding 15 minutes) and magnitude of these trends (e.g., humidity lower than 1%, load increase exceeding 3%, quality decrease exceeding 0.5%) both meet preset thresholds, and a specific proportional relationship exists between the rate of change of the operating load information and the rate of change of the shaped granule quality information, the system will determine that there is a deviation in the material humidity measurement device. In this way, the system can distinguish this deviation from slight signal fluctuations caused by only a slight change in the fiber length of the material due to a change in raw material batches, thereby avoiding interference with the normal production process and promptly issuing sensor calibration or inspection prompts.

[0059] In some embodiments, the step of adjusting the degree of confidence in the material humidity information to obtain an adjusted material humidity value when the operating status indicates that the material humidity measuring device has a deviation includes:

[0060] Obtain the type of deviation from the material moisture measuring device;

[0061] To determine the degree of deviation of the material moisture measuring device;

[0062] Match the preset deviation pattern according to the deviation type and degree;

[0063] Based on the deviation pattern, assess the effective information content of the material moisture measurement device;

[0064] Generate acceptance weight coefficients based on the effective information content;

[0065] The material humidity information is integrated with the acceptance weighting coefficient to obtain the material humidity adjustment value.

[0066] Specifically, identifying the type of deviation in a material moisture measurement device refers to recognizing specific abnormal patterns exhibited by the device, such as systematic errors, random errors, drift, calibration failure, or sensor damage. These types can be identified through analysis of historical data, diagnostic logs, or specific test patterns. The degree of deviation in a material moisture measurement device can be understood as the magnitude of the deviation between the measured value and the true value, expressed as a percentage, absolute value, or standard deviation, with the aim of quantifying the severity of the deviation.

[0067] Based on the type and degree of deviation, matching a preset deviation pattern involves comparing the currently diagnosed deviation characteristics with a pre-established knowledge base. This knowledge base contains typical behavioral patterns corresponding to different types and degrees of deviation; for example, a certain type of sensor drift may correspond to a specific output curve change pattern. Furthermore, based on matching the preset deviation pattern, evaluating the effective information content of the material humidity measuring device means determining the portion of the data provided by the measuring device that still has reference value under the current deviation conditions. For example, if the sensor has a slight systematic deviation, its trend information may still be valid, but the absolute value may need correction.

[0068] Based on the effective information content, the confidence weight coefficient is calculated as a value between 0 and 1, representing the degree of trust in the material humidity information. The higher the effective information content, the larger the confidence weight coefficient, and vice versa. Therefore, the material humidity information is fused with the confidence weight coefficient to obtain the material humidity adjustment value. The fusion method can be to multiply the material humidity information by the confidence weight coefficient, or to use algorithms such as weighted averaging or Kalman filtering, combined with other reliable information sources (such as indirect physical feedback information) for comprehensive correction, thus obtaining a more accurate material humidity adjustment value.

[0069] This application employs a refined diagnostic approach to the deviation of a material moisture measurement device. First, it identifies the type and degree of deviation, then matches it to a preset deviation pattern. This meticulous diagnostic process allows for an accurate assessment of the effective information content of the measurement device under its current deviation condition. Based on this, the system generates a confidence weighting coefficient directly correlated with the effective information content. This coefficient precisely reflects the level of trust in the material moisture information. By integrating the material moisture information with this confidence weighting coefficient, the original measurement value can be specifically corrected, avoiding the inaccuracies that may result from general adjustments and ensuring the reliability of the adjusted material moisture value.

[0070] In some embodiments, the step of issuing a prompt message for the material moisture measuring device when the operating status indicates a deviation in the material moisture measuring device includes:

[0071] Obtain the type of deviation from the material moisture measuring device;

[0072] To determine the degree of deviation of the material moisture measuring device;

[0073] Match preset diagnostic details based on the type and degree of deviation;

[0074] Based on the type and degree of deviation, match the preset operation suggestions;

[0075] Generate prompts containing diagnostic details and operational suggestions;

[0076] Adjust the urgency level of the alert message based on the degree of deviation.

[0077] Specifically, the type of deviation acquired by the material moisture measurement device refers to the specific nature of the deviation identified by the system through analysis of sensor data, historical fault records, or comparison with other indirect physical feedback information. Examples of deviations include sensor reading drift, data jumps, complete failure, or hysteresis. The degree of deviation acquired refers to the quantification of the severity of the deviation, such as slight, moderate, or severe. This can be assessed by the degree of deviation from the normal range, its duration, or the potential risk to production.

[0078] Matching preset diagnostic details based on the type and severity of deviation means that the system internally stores detailed fault descriptions and possible causes for different types and degrees of deviation. When a specific deviation is identified, the corresponding explanatory information is automatically retrieved. For example, for sensor reading drift with moderate deviation, diagnostic details might include that the sensor's long-term output value deviates from the normal range, possibly caused by sensor aging or surface contamination. Simultaneously, matching preset operational suggestions based on the type and severity of deviation means that the system provides targeted solutions or maintenance guidance, such as recommending checking the sensor surface cleanliness, performing calibration, and replacing the sensor if necessary.

[0079] The system generates prompts that include diagnostic details and operational suggestions, ensuring the comprehensiveness and usability of the information. In practical applications, the urgency level of the prompts is adjusted based on the degree of deviation. For example, minor deviations are set to "General," moderate deviations to "Warning," and severe deviations to "Urgent." This helps operators prioritize issues based on their urgency, ensuring that critical problems are addressed promptly.

[0080] This application overcomes the limitations of vague prompts by finely identifying and quantifying the deviation of material moisture measuring devices. Because it obtains the specific type and degree of deviation, the system can accurately match preset diagnostic details and operational suggestions. This matching mechanism ensures that the generated prompts are no longer simple fault notifications, but rather include in-depth analysis of the problem's nature and actionable solutions. Furthermore, by adjusting the urgency level of the prompts based on the degree of deviation, this application's solution ensures the effectiveness and prioritization of information delivery, allowing operators to rationally allocate attention and resources according to the severity of the problem, thereby avoiding slow responses caused by information overload or unclear prioritization.

[0081] In some embodiments, the step of inferring the actual moisture content of the material based on the operating load information includes:

[0082] Acquire information on the wear degree of the ring die of the molding machine, the particle size distribution of the raw material, the amount of binder added, and the fluctuation of the molding temperature;

[0083] Based on information on ring die wear, raw material particle size distribution, binder addition amount, and molding temperature fluctuation, the operating load information is corrected to obtain the corrected operating load information.

[0084] Based on the corrected operating load information, the actual moisture content of the material is inferred.

[0085] The information includes: Ring die wear information (associated with biomass pelleting), the size and shape of the die due to friction during use, the temperature fluctuations, and the temperature fluctuations of the pellets. The ring die wear alters the stress distribution and compression resistance of the material within the die orifice, thus affecting the operating load. This information can be obtained by periodically monitoring the inner diameter and depth of the ring die orifice, or by using sensors to monitor wear. The particle size distribution of the raw material refers to the size, shape, and proportion of biomass pellets in the overall composition. Different particle size distributions affect the bulk density, flowability, and compressibility of the material during pelleting, thus influencing the pelleting load. This information can be obtained through sieving analysis, image recognition, etc. The amount of binder added refers to the actual amount of binder (such as starch or lignin) added to the biomass raw material. The amount of binder added directly affects the material's bonding properties and plasticity during pelleting, thereby altering the required operating load. This information is typically provided by a metering device. The temperature fluctuation information refers to the temperature changes of the ring die or material during the pelleting process. Temperature affects the plasticization and bonding properties of the material, especially in biomass pelleting, where temperature is crucial for softening lignin; therefore, temperature fluctuations significantly impact the operating load. This information can be monitored in real time using a temperature sensor.

[0086] Correcting the operating load information involves using the aforementioned information on ring die wear, raw material particle size distribution, binder dosage, and molding temperature fluctuations. Through mathematical models or table lookups, the contribution or interference of these factors to the original operating load information is calculated and then subtracted from or adjusted to eliminate their influence on the inference of material moisture content. For example, a multiple regression model can be established, with operating load as the dependent variable and material moisture content, ring die wear, particle size distribution, binder dosage, and molding temperature as independent variables. The model can then deduce the operating load component caused solely by material moisture content, after excluding the influence of other factors. The resulting corrected operating load information, after the above correction process, more accurately reflects the actual moisture content of the material.

[0087] This application aims to isolate the interference components caused by non-moisture-containing factors from the operating load information by introducing information on ring die wear, raw material particle size distribution, binder dosage, and molding temperature fluctuation. Specifically, ring die wear increases extrusion resistance, which may increase the operating load even if the material's moisture content remains unchanged; changes in raw material particle size distribution affect the material's filling density and friction, thus altering the operating load; increases or decreases in binder dosage directly affect the material's plasticity and adhesion, thereby changing the energy required for molding; and fluctuations in molding temperature affect the material's plasticization effect, particularly significantly impacting the softening degree of lignin, thus affecting molding resistance. By acquiring and quantifying the influence of these factors, a correction model can be established to compensate for the deviations caused by these factors in the original operating load information. The resulting corrected operating load information can more purely and accurately reflect the actual moisture content of the material, thus providing a more reliable basis for subsequent humidification adjustment commands.

[0088] In some embodiments, the step of inferring the actual moisture content of the material based on the operating load information includes:

[0089] Continuously monitor the operating load information of the molding machine and obtain the changing trend of the operating load information;

[0090] Based on a pre-defined mapping relationship reflecting the material's response characteristics to operating load in different moisture content ranges, the mapping relationship between operating load information and material moisture content is dynamically adjusted according to the changing trend of operating load information. Based on the dynamically adjusted mapping relationship, the actual moisture content of the material is inferred, wherein:

[0091] When the change in operating load information does not reach the preset threshold, the density change information of the formed particles is obtained, and the mapping relationship between operating load information and material moisture content is adjusted in combination with the density change information.

[0092] When there is a lag in the correlation between material moisture content and operating load information, the rate and direction of change of operating load information are obtained, and the future trend of material moisture content is predicted using the rate and direction of change. Based on the future trend, the mapping relationship between operating load information and material moisture content is adjusted.

[0093] When the molding temperature fluctuates, the fluctuation range of the molding temperature is obtained, and the mapping relationship between the operating load information and the moisture content of the material is compensated and adjusted according to the fluctuation range to eliminate the influence of the molding temperature on the accuracy of the inference.

[0094] Specifically, continuous monitoring of the molding machine's operating load information refers to collecting data such as drive motor current, power, or torque in real time through sensors, and processing this data to obtain the instantaneous value and long-term trend of the operating load. The trend of the operating load information can be understood as the pattern of how the operating load changes over time, such as whether it increases, decreases, or remains stable, as well as the rate and magnitude of change.

[0095] The preset mapping relationship reflecting the response characteristics of materials to operating load in different moisture content ranges can be understood as the typical performance of the molding machine's operating load under different material moisture contents. For example, when the material is too wet, the operating load may be low and fluctuate greatly; when the material is too dry, the operating load may be high and stable. Dynamically adjusting the mapping relationship between operating load information and material moisture content means that, based on the actual monitored trend of operating load changes and combined with other auxiliary information, this preset correlation is corrected and optimized in real time to make it closer to the current actual working conditions.

[0096] When the change in operating load information does not reach a preset threshold, it means that the change in operating load is insufficient to clearly indicate a significant change in the material's moisture content. In this case, obtaining information on the density change of the formed particles can serve as an auxiliary basis for judgment. For example, a small change in the material's moisture content may lead to subtle fluctuations in the density of the formed particles. By combining this density change information, the mapping relationship can be adjusted more accurately, thereby inferring the actual moisture content of the material.

[0097] When there is a lag in the correlation between material moisture content and operating load information—meaning changes in operating load do not immediately reflect the true changes in the material's moisture content—it is necessary to obtain the rate and direction of change in operating load information. Using this information, future trends in the material's moisture content can be predicted. For example, if the operating load continues to increase at a certain rate, even if the current material moisture content has not changed significantly, it can be predicted that it will tend to dry out. Based on this future trend, the mapping relationship can be adjusted in advance to cope with upcoming changes in the material's state.

[0098] When the molding temperature fluctuates, the increase or decrease in molding temperature affects the plasticity of the material and the friction during the molding process, thus affecting the operating load. Therefore, obtaining the fluctuation range of the molding temperature and compensating for the mapping relationship between the operating load information and the moisture content of the material based on this fluctuation range can effectively eliminate the interference of temperature fluctuations on the accuracy of inferences and ensure the reliability of the inference results.

[0099] This application addresses the problem of insufficient accuracy in inference under complex working conditions caused by static mapping by introducing continuous monitoring of changes in operating load information and dynamic adjustment of the mapping relationship. Specifically, by continuously monitoring the changing trend of operating load information, the system can perceive dynamic changes in the molding process in real time. When the change in operating load information is insufficient to clearly indicate the moisture content of the material, the density change information of the molded particles is used as an auxiliary judgment, enabling even small changes in moisture content to be effectively identified, thus avoiding misjudgments caused by the insensitivity of a single indicator. When there is a lag in the correlation between the material moisture content and operating load information, the future trend of the material moisture content can be predicted by analyzing the rate and direction of change of operating load information, thereby enabling advance adjustment of the mapping relationship, effectively responding to dynamic changes, and avoiding control deviations caused by lag. In addition, by compensating for fluctuations in molding temperature, the influence of temperature changes on the relationship between operating load and material moisture content is eliminated, ensuring the accuracy and stability of inference under different temperature conditions. It is precisely because of these multi-dimensional, adaptive adjustment mechanisms that the inference of the actual moisture content of the material becomes more accurate and robust.

[0100] The following is a specific example to illustrate this.

[0101] Suppose that during the biomass fuel pelleting process, the moisture content of the material slightly decreases, but due to the inertia of the pelleting machine's operating load or the buffering effect of the material itself, the change in operating load information has not yet reached the preset significant threshold. If only the static mapping relationship of operating load is relied upon, the system may not be able to identify this slight decrease in moisture content in time, resulting in insufficient humidification and affecting the pelleting quality.

[0102] According to the scheme of this application, when the system detects that the change in operating load information does not reach a preset threshold, it will further acquire information on the density change of the shaped particles. For example, if it finds that the density of the shaped particles begins to show a slight but continuous upward trend (usually, a decrease in material moisture content will lead to an increase in particle density), the system will combine this density change information to fine-tune the mapping relationship between operating load and material moisture content. This adjustment enables the system to more sensitively capture subtle changes in material moisture content, and even if the change in operating load is not significant, it can accurately infer the slight decrease in the actual moisture content of the material.

[0103] Suppose that during the production process, changes in raw material batches or ambient temperature cause a lag in the correlation between material moisture content and operating load. For example, the material moisture content may have already begun to decrease, but the increasing trend of the operating load may not yet be apparent. In this case, the solution in this application continuously acquires the rate and direction of change of the operating load information. If the system detects that although the current change in the operating load is not significant, its rate of change shows a continuous, slight upward trend, and based on historical data analysis, it determines that this trend indicates a further decrease in the material moisture content, the system will use this predicted future trend to adjust the mapping relationship in advance. For example, it can correct the inferred moisture content corresponding to the current operating load downward, thereby issuing an instruction to increase the humidification amount in advance, avoiding particle quality problems caused by the lag.

[0104] When the molding temperature fluctuates due to external environmental factors or the equipment's own heat generation, such as an increase in molding temperature, the material may become more easily plasticized, resulting in a slight decrease in operating load at the same moisture content. If this temperature effect is not compensated for, the system may misjudge that the material's moisture content has increased. The solution in this application acquires the fluctuation range of the molding temperature and, based on a preset compensation model, adjusts the mapping relationship between operating load information and the material's moisture content. For example, when the temperature increases, the system correspondingly improves the correlation between operating load and moisture content, making the inferred moisture content under the same operating load closer to the true value, thereby eliminating the impact of temperature fluctuations on the accuracy of the inference. Through these dynamic and multi-dimensional adjustments, the solution in this application ensures that the inference of the actual moisture content of the material remains highly accurate under various complex operating conditions, providing a reliable guarantee for the stable production of biomass fuel pellets.

[0105] In some embodiments, the step of obtaining density change information of the molded particles when the change in operating load information does not reach a preset threshold, and adjusting the mapping relationship between operating load information and material moisture content based on the density change information, includes:

[0106] Continuously acquire density information of the formed particles and perform real-time fluctuation analysis on the density information to obtain the fluctuation amplitude and frequency of the density information;

[0107] When the change in operating load information does not reach the preset threshold and the density information of the formed particles is within a small fluctuation range, the fluctuation amplitude and fluctuation frequency of the density information are compared with the preset density fluctuation characteristics that reflect slight changes in the moisture content of the material.

[0108] If the fluctuation amplitude and frequency of density information do not match the preset density fluctuation characteristics when the material moisture content changes slightly, then further compare the fluctuation amplitude and frequency of density information with the preset density fluctuation characteristics that reflect the slight differences between raw material batches or the local unevenness of mold temperature.

[0109] Based on the comparison results, it can be determined whether the density fluctuation is caused by a slight change in the moisture content of the material or by other minor disturbance factors.

[0110] When the cause is determined to be a slight change in the material's moisture content, the mapping relationship between the operating load information and the material's moisture content is adjusted by combining the density change information.

[0111] When the problem is determined to be caused by other minor interference factors, a prompt message will be issued to indicate the presence of minor interference factors.

[0112] Specifically, continuously acquiring the density information of the formed particles and performing real-time fluctuation analysis to obtain the amplitude and frequency of density fluctuations refers to continuously monitoring the density of the particles produced by the forming machine and using statistical methods or signal processing techniques to analyze the range and rate of change over a short period of time. For example, methods such as moving average, standard deviation calculation, or Fourier transform can be used to quantify the amplitude and frequency of density fluctuations. The purpose is to capture subtle changes in particle density, providing basic data for subsequent judgments.

[0113] When the change in operating load information does not reach a preset threshold, and the density information of the formed particles is within a small fluctuation range, comparing the fluctuation amplitude and frequency of density information with preset density fluctuation characteristics reflecting slight changes in material moisture content means comparing the currently observed density fluctuation characteristics with a density fluctuation pattern caused by slight changes in typical material moisture content, established in advance through experiments or historical data, when the change in operating load is not significant and the particle density fluctuation is small. For example, when the moisture content increases slightly, the particle density may show a decreasing trend in amplitude and frequency.

[0114] If the fluctuation amplitude and frequency of density information do not match the preset density fluctuation characteristics when the material moisture content changes slightly, the system will further compare the fluctuation amplitude and frequency of density information with the preset density fluctuation characteristics that reflect the slight differences between raw material batches or the local unevenness of mold temperature. This means that when it is initially determined that the density fluctuation is not caused by the slight change in moisture content, the system will further compare the current density fluctuation characteristics with the preset mode that reflects other interfering factors (such as density baseline drift caused by changes in raw material batches, or particle density unevenness caused by local overheating / overcooling of the mold).

[0115] Based on the comparison results, distinguishing whether density fluctuations are caused by slight changes in material moisture content or by other minor disturbance factors means that through the above multiple comparisons and pattern recognition, the system can intelligently determine whether the currently observed particle density fluctuations truly reflect slight changes in material moisture content or are caused by other non-moisture content factors (such as raw material characteristics, equipment status, etc.).

[0116] When the cause is determined to be a slight change in the material's moisture content, the mapping relationship is adjusted by combining density change information. This means that once it is confirmed that the density fluctuation is caused by a slight change in the material's moisture content, the system will use this density change information to accurately correct the mapping relationship between the operating load and the material's moisture content, thereby improving the accuracy of the inference.

[0117] When the issue is determined to be caused by other minor disturbances, the system ignores the density change information used to correct the material's moisture content and issues a warning message indicating the presence of minor disturbances. This means that if the density fluctuation is determined to be caused by non-moisture content factors, the system will not use this density change information to correct the material's moisture content inference, thus avoiding introducing errors. Simultaneously, the system will issue a warning message to the operator, pointing out potential disturbances, such as slight differences in raw material batch characteristics or abnormal local temperatures in the mold, so that the operator can inspect and intervene.

[0118] This application addresses the potential misjudgment issues in inferring the moisture content of materials by introducing multi-dimensional data analysis and intelligent pattern recognition mechanisms. Specifically, when the operating load changes insignificantly, the system no longer simply relies on density change information. Instead, it continuously acquires the density information of the formed particles and performs real-time fluctuation analysis to obtain the fluctuation amplitude and frequency. Simultaneously, it acquires key characteristic parameters of the current raw material batch, such as fiber length distribution and lignin content, providing baseline information about the material itself for subsequent judgments. When the change amplitude of the operating load information does not reach a preset threshold, and the density information of the formed particles is within a small fluctuation range, the system first compares the current density fluctuation characteristics with preset density fluctuation characteristics reflecting slight changes in material moisture content. If the two do not match, it further compares with preset density fluctuation characteristics reflecting subtle differences between raw material batches or localized uneven mold temperature. Through this progressive comparison and identification, the system can accurately distinguish whether the density fluctuation is caused by a slight change in material moisture content or by other minor interfering factors. Only when it is confirmed that the density fluctuation is caused by a slight change in material moisture content is the mapping relationship adjusted in conjunction with the density change information to ensure the effectiveness of the adjustment. Conversely, when the cause is determined to be other minor disturbance factors, the correction inference of the density change information on the material's moisture content is ignored, avoiding incorrect adjustments due to misjudgment. The system also issues timely warnings indicating the presence of minor disturbance factors, thereby guiding operators to conduct targeted troubleshooting and improving the system's intelligence level and fault diagnosis capabilities.

[0119] The following is a specific example to illustrate this.

[0120] Assuming the biomass fuel pellet mill is operating stably, the humidity value indicated by the material moisture measurement device does not fluctuate significantly, and the change in the operating load information of the drive components does not reach the preset threshold. However, the system continuously monitors slight fluctuations in the density information of the formed pellets; for example, the density value changes from 1.15 g / cm³ in a short period of time. 3 Slightly decreased to 1.14 g / cm³ 3 The fluctuation range was 0.01 g / cm³. 3 The fluctuation frequency is twice per minute.

[0121] At this point, the system first analyzes the amplitude and frequency of the density fluctuation. Based on preset association rules, the system compares the data and finds that this density fluctuation in amplitude and frequency highly matches the density fluctuation characteristics recorded in historical data when the material's moisture content slightly increases by 0.5%. Therefore, the system determines that the density fluctuation is caused by a slight change in the material's moisture content. Based on this judgment, the system, in conjunction with this density change information, fine-tunes the mapping relationship between operating load and material moisture content; for example, it slightly shifts the mapping curve upwards to more accurately reflect the current actual moisture content of the material.

[0122] In contrast, in another scenario, if the system detects similar density fluctuations, but comparison reveals that these fluctuations do not match the preset characteristics of slight changes in material moisture content, the system will further compare these fluctuations with preset density fluctuations caused by minor differences between raw material batches or localized uneven mold temperature. Suppose the system ultimately determines that the density fluctuation matches the particle binding characteristics caused by a slight increase in lignin content in the current raw material batch. In this case, the system will ignore the correction inference of the material's moisture content based on this density change information, as it is not caused by moisture content. Simultaneously, the system will issue a prompt to the operator, such as: "Slight differences in raw material batch characteristics detected; please observe the particle forming quality," thus avoiding incorrect humidification adjustments and guiding the operator to focus on raw material quality or make corresponding process parameter adjustments.

[0123] In some embodiments, when a lag occurs in the correlation between material moisture content and operating load information, the steps of obtaining the rate and direction of change of operating load information, using the rate and direction of change to predict the future trend of material moisture content, and adjusting the mapping relationship between operating load information and material moisture content based on the future trend include:

[0124] When there is a lag in the correlation between material moisture content and operating load information, the rate and direction of change of operating load information should be continuously acquired.

[0125] At the same time, real-time temperature and exhaust humidity information of the formed particles are obtained;

[0126] Cross-compare the rate and direction of change of operating load information, the real-time temperature information of the formed particles, and the exhaust humidity information to identify whether there are signs of trend reversal.

[0127] When signs of a trend reversal are detected, the mapping relationship between operating load information and material moisture content is adjusted based on the detected signs of a trend reversal.

[0128] Specifically, when there is a lag in the correlation between material moisture content and operating load information, it means that changes in material moisture content are not immediately or synchronously reflected in the operating load of the molding machine, or there is a certain time delay between changes in operating load and changes in material moisture content. In this case, the system will continuously collect and analyze the rate and direction of change of the molding machine's operating load to preliminarily determine the dynamic trend of the material's moisture content.

[0129] Real-time temperature information for the formed particles refers to the temperature data of the particle surface or interior obtained by temperature sensors installed at the mold outlet or particle cooling area during the forming process. Exhaust humidity information refers to the humidity of the exhaust gas measured at the exhaust port of the forming machine, reflecting the rate of moisture evaporation from the material during forming. This information serves as supplementary judgment, providing more direct clues about the internal state of the material and the rate of moisture evaporation.

[0130] Cross-comparing the rate and direction of change in operating load information, real-time temperature information of molded particles, and exhaust humidity information aims to more accurately identify the true changes in the moisture content of materials through comprehensive analysis of multi-source data, especially whether there are signs of trend reversal. For example, when the operating load information shows a continuous increase, but the real-time temperature and exhaust humidity of the molded particles begin to decrease, this may indicate that the moisture content of the material has reached a certain critical point and has begun to decrease. The increase in operating load is a manifestation of hysteresis effect or increased friction, rather than a direct reflection of a continuous increase in moisture content.

[0131] When signs of trend reversal are detected, such as a deviation between the operating load trend and the temperature and humidity trends found through the aforementioned cross-comparison, and this deviation conforms to a preset trend reversal pattern, the system will immediately adjust the mapping relationship between the operating load information and the material moisture content based on the detected trend reversal signs. This adjustment aims to correct misjudgments caused by lag, enabling the mapping relationship to reflect the actual moisture content of the material more timely and accurately.

[0132] This application effectively addresses the problem of inaccurate inferences that may arise from relying solely on operating load information when there is a lag in the correlation between material moisture content and operating load. This is achieved by introducing real-time temperature and exhaust humidity information of the formed particles and cross-referencing multi-source data. Because changes in material moisture content directly affect the frictional heat generation during the forming process (reflected in particle temperature) and moisture evaporation (reflected in exhaust humidity), these auxiliary information provide immediate feedback on the internal state of the material. When operating load information fails to reflect the true changes in material moisture content due to lag, changes in particle temperature and exhaust humidity serve as more sensitive indicators, helping the system identify the true trend of material moisture content, especially when the material moisture content is about to reverse. Through comprehensive analysis of this information, the system can detect signs of trend reversal earlier and more accurately, thereby avoiding erroneous judgments and inappropriate adjustments to mapping relationships caused by lag effects.

[0133] The following is a specific example to illustrate this.

[0134] Assuming that during the biomass fuel pellet forming process, due to the complexity of material characteristics or equipment operating conditions, a slight decrease in the moisture content of the material may not immediately lead to a significant decrease in the operating load of the pelleting machine. Instead, the operating load may remain high or even increase slightly due to a temporary increase in the internal friction of the material, thus resulting in a lag in the correlation between the moisture content of the material and the operating load information.

[0135] In this scenario, if the system relies solely on the rate and direction of change in the operating load information, it might incorrectly determine that the material moisture content remains high or continues to rise, thus issuing unnecessary humidification commands. However, according to the solution in this application, the system continuously acquires the real-time temperature and exhaust humidity information of the formed particles while simultaneously acquiring the rate and direction of change in the operating load information. For example, when the operating load information shows a slow increase or remains stable, but the system simultaneously detects that the real-time temperature of the formed particles begins to decrease slowly, and the exhaust humidity also shows a decreasing trend, this auxiliary information provides strong evidence that the material moisture content is actually decreasing.

[0136] By cross-referencing the rate and direction of change in operating load information, the real-time temperature of the formed particles, and the exhaust humidity information, the system can identify signs of a trend reversal between an increase / stable operating load and a decrease in particle temperature / exhaust humidity. This indicates that although there is a lag in the direct response of the operating load, the actual moisture content of the material has begun to decrease. Once this trend reversal is identified, the system will adjust the mapping relationship between the operating load information and the material's moisture content based on these comprehensive judgments. For example, it can map the current operating load value to a lower material moisture content range, thereby avoiding issuing incorrect humidification commands, ensuring precise control of the humidification amount, and preventing over- or under-humidification of the material.

[0137] In some embodiments, the steps described above, such as acquiring the fluctuation range of the molding temperature when the molding temperature fluctuates, and compensating for and adjusting the mapping relationship between the operating load information and the moisture content of the material based on the fluctuation range to eliminate the influence of the molding temperature on the accuracy of the inference, include:

[0138] Continuously monitor the fluctuation amplitude, frequency, and direction of the molding temperature;

[0139] Based on the fluctuation amplitude, frequency, and direction of the molding temperature, and combined with a pre-set compensation model that reflects the influence of different temperature fluctuation characteristics on the mapping relationship between operating load information and material moisture content, the mapping relationship between operating load information and material moisture content is dynamically compensated and adjusted.

[0140] Specifically, continuously monitoring the amplitude, frequency, and direction of temperature fluctuations in the molding process involves collecting temperature data in real time through temperature sensors installed inside or outside the molding machine. Analyzing this real-time data allows us to extract the amplitude of temperature changes (i.e., the difference between the highest and lowest temperatures or the deviation from a reference temperature), the frequency of temperature fluctuations (i.e., the number of temperature fluctuations per unit time), and the direction of temperature fluctuations (i.e., whether the temperature is trending upwards, downwards, or fluctuating periodically). The acquisition of these parameters aims to provide more comprehensive information on the characteristics of temperature fluctuations, rather than just the amplitude of a single fluctuation.

[0141] The inclusion of a pre-set compensation model reflecting the impact of different temperature fluctuation characteristics on the mapping relationship between operating load information and material moisture content can be understood as establishing an intelligent compensation mechanism. This compensation model is pre-trained and set based on a large amount of historical data and experimental results. It can quantify the degree and manner in which different types of temperature fluctuations (e.g., small-amplitude high-frequency fluctuations, large-amplitude low-frequency fluctuations, continuous upward or downward trends, etc.) affect the mapping relationship between operating load and material moisture content. For example, when the temperature rises rapidly, the evaporation of internal moisture in the material accelerates, which may cause the actual moisture content to be lower than the sensor reading. In this case, the model will instruct adjustments to the mapping relationship in a specific direction and magnitude.

[0142] Dynamic compensation and adjustment are performed on the mapping relationship between operating load information and material moisture content. Specifically, this involves real-time correction of the correlation curve or parameters between operating load information and material moisture content based on the monitored fluctuation amplitude, frequency, and direction of molding temperature, as well as the output of the compensation model. This dynamic adjustment ensures that the actual moisture content of the material inferred from the operating load information remains highly accurate even when the molding temperature changes continuously. For example, if temperature fluctuations cause a specific value of the operating load to now correspond to a higher actual moisture content, the mapping relationship will be shifted upwards or its slope adjusted accordingly.

[0143] This application, by continuously monitoring the fluctuation amplitude, frequency, and direction of molding temperature, and combining this with a pre-set compensation model, can more comprehensively and precisely capture the dynamic characteristics of molding temperature changes. It is precisely because the multi-dimensional characteristics of temperature fluctuations are considered, rather than just the single fluctuation amplitude, that the compensation model can more accurately assess the impact of temperature fluctuations on the mapping relationship between operating load and material moisture content. Based on this, by dynamically compensating and adjusting the mapping relationship, the interference of complex molding temperature fluctuations on the accuracy of inferring the actual moisture content of the material is effectively eliminated, thus overcoming the limitations that may exist in compensation based solely on fluctuation amplitude.

[0144] Assume that during the operation of a biomass fuel pellet forming machine, the forming temperature fluctuates periodically due to changes in ambient temperature or heat accumulation inside the equipment. For example, the temperature might rise from 80°C to 85°C within 2 minutes, and then drop back to 80°C within 2 minutes, forming a fluctuation range of 5°C at a frequency of 0.25 times / minute. Traditional compensation methods might only adjust based on this 5°C fluctuation range. However, the solution proposed in this application continuously monitors this 5°C fluctuation range, the fluctuation frequency of 0.25 times / minute, and the direction of the periodic rise and fall. The system will adjust according to a preset compensation model, which may include compensation parameters for this specific fluctuation pattern. For example, when the temperature fluctuates periodically with a specific frequency and amplitude, the mapping relationship between the operating load and the material moisture content needs to be shifted upward by X units to reflect the slight changes in the actual moisture content of the material. Through this dynamic and multi-dimensional compensation adjustment, even in an environment with continuous temperature fluctuations, the system can accurately infer the actual moisture content of the material, thereby issuing more precise humidification commands and ensuring the stability of pellet forming quality.

[0145] like Figure 2 As shown in the figure, this application discloses a temperature and humidity control system for a biomass fuel pellet forming machine, including:

[0146] Material humidity information acquisition module 1 is used to acquire material humidity information provided by the material humidity measuring device;

[0147] The indirect physical feedback information acquisition module 2 is used to acquire indirect physical feedback information, which includes the operating load information of the components driving the molding machine, the quality information of the molded particles, and the execution information of humidification adjustment.

[0148] The operation status judgment module 3 is used to judge the material humidity information, operating load information, quality information of shaped particles, and execution information of humidification adjustment, so as to identify the difference between the material humidity information and the indirect physical feedback information, and determine the operation status of the material humidity measuring device.

[0149] The confidence level adjustment module 4 is used to adjust the confidence level of the material humidity information when the operating status indicates that there is a deviation in the material humidity measuring device, and obtain the material humidity adjustment value.

[0150] Actual moisture content inference module 5 is used to infer the actual moisture content of the material based on the operating load information;

[0151] The humidification amount instruction issuing module 6 is used to issue instructions to adjust the humidification amount based on the material's actual moisture content and humidity adjustment value.

[0152] The prompt message issuing module 7 is used to issue a prompt message for the material humidity measuring device when the operating status indicates that there is a deviation in the material humidity measuring device.

[0153] The system proposed in this application can effectively avoid the risks of decreased production efficiency, deterioration of product quality, and equipment damage caused by sensor deviation.

[0154] The above are merely embodiments of this application and are not intended to limit the scope of protection of this application. Various modifications and variations can be made to this application by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this application should be included within the scope of protection of this application.

Claims

1. A method for controlling temperature and humidity in a biomass fuel pellet molding machine, characterized by, include: Obtain material humidity information provided by the material humidity measuring device; Obtain indirect physical feedback information, which includes the operating load information of the components driving the molding machine, the quality information of the molded particles, and the execution information of humidification adjustment; The system assesses material humidity information, operating load information, granule quality information, and humidification adjustment execution information to identify discrepancies between material humidity information and indirect physical feedback information, and to determine the operating status of the material humidity measuring device. When the operating status indicates that the material humidity measuring device has a deviation, the degree of confidence in the material humidity information is adjusted to obtain the material humidity adjustment value; Based on the operating load information, infer the actual moisture content of the material; Based on the actual moisture content of the material and the material humidity adjustment value, an instruction is issued to adjust the humidification amount. When the operating status indicates that the material moisture measuring device has a deviation, a prompt message from the material moisture measuring device will be issued.

2. The method according to claim 1, wherein The steps of judging material humidity information, operating load information, shaped particle quality information, and humidification adjustment execution information to identify the differences between material humidity information and indirect physical feedback information, and to determine the operating status of the material humidity measuring device, include: Trend analysis was performed on the continuously collected material humidity information, operating load information, shaped particle quality information, and humidification regulation execution information to extract the rate and cumulative change of material humidity information, operating load information, shaped particle quality information, and humidification regulation execution information. Determine whether a persistently low trend in material moisture information occurs simultaneously with a slow, cumulative upward trend in operating load information; Determine whether there is a specific time correlation between the slow cumulative increase trend of operating load information and the slow decrease trend of shaped particle quality information; When the material moisture information shows a continuous low trend, the operating load information shows a slow cumulative increase trend, and the shaped particle quality information shows a slow decrease trend, all of which simultaneously meet the preset duration threshold and change range threshold, and there is a preset correlation between the change rate of the operating load information and the change rate of the shaped particle quality information, it is determined that there is a deviation in the operation of the material moisture measurement device.

3. The method according to claim 1, wherein The step of adjusting the reliability of the material humidity information to obtain an adjusted material humidity value when the operating status indicates that the material humidity measuring device has a deviation includes: Obtain the type and degree of deviation of the material moisture measuring device; Match the preset deviation pattern according to the deviation type and degree; Based on the deviation pattern, assess the effective information content of the material moisture measurement device; Generate acceptance weight coefficients based on the effective information content; The material humidity information is integrated with the acceptance weighting coefficient to obtain the material humidity adjustment value.

4. The method according to claim 1, wherein The step of issuing a prompt message for the material moisture measuring device when the operating status indicates a deviation includes: Obtain the type and degree of deviation of the material moisture measuring device; Based on the type and degree of deviation, match preset diagnostic details and preset operational suggestions; Generate prompts containing diagnostic details and operational suggestions; Adjust the urgency level of the alert message based on the degree of deviation.

5. The method of claim 1, wherein the temperature and humidity of the biomass fuel pellet molding machine is controlled. The step of inferring the actual moisture content of the material based on the operating load information includes: Acquire information on the wear degree of the ring die of the molding machine, the particle size distribution of the raw material, the amount of binder added, and the fluctuation of the molding temperature; Based on information on ring die wear, raw material particle size distribution, binder addition amount, and molding temperature fluctuation, the operating load information is corrected to obtain the corrected operating load information. Based on the corrected operating load information, the actual moisture content of the material is inferred.

6. The method of claim 1, wherein the temperature and humidity of the biomass fuel pellet molding machine is controlled. The step of inferring the actual moisture content of the material based on the operating load information includes: Continuously monitor the operating load information of the molding machine and obtain the changing trend of the operating load information; Based on a pre-defined mapping relationship reflecting the material's response characteristics to operating load in different moisture content ranges, the mapping relationship between operating load information and material moisture content is dynamically adjusted according to the changing trend of operating load information. Based on the dynamically adjusted mapping relationship, the actual moisture content of the material is inferred, wherein: When the change in operating load information does not reach the preset threshold, the density change information of the formed particles is obtained, and the mapping relationship between operating load information and material moisture content is adjusted in combination with the density change information. When there is a lag in the correlation between material moisture content and operating load information, the rate and direction of change of operating load information are obtained, and the future trend of material moisture content is predicted using the rate and direction of change. Based on the future trend, the mapping relationship between operating load information and material moisture content is adjusted. When the molding temperature fluctuates, the fluctuation range of the molding temperature is obtained, and the mapping relationship between the operating load information and the moisture content of the material is compensated and adjusted according to the fluctuation range to eliminate the influence of the molding temperature on the accuracy of the inference.

7. The method for controlling temperature and humidity in a biomass fuel pellet forming machine according to claim 6, characterized in that, The step of obtaining density change information of the formed particles when the change in operating load information does not reach a preset threshold, and adjusting the mapping relationship between operating load information and material moisture content based on the density change information, includes: Continuously acquire density information of the formed particles and perform real-time fluctuation analysis on the density information to obtain the fluctuation amplitude and frequency of the density information; When the change in operating load information does not reach the preset threshold and the density information of the formed particles is within a small fluctuation range, the fluctuation amplitude and fluctuation frequency of the density information are compared with the preset density fluctuation characteristics that reflect slight changes in the moisture content of the material. If the fluctuation amplitude and frequency of density information do not match the preset density fluctuation characteristics when the material moisture content changes slightly, then further compare the fluctuation amplitude and frequency of density information with the preset density fluctuation characteristics that reflect the slight differences between raw material batches or the local unevenness of mold temperature. Based on the comparison results, it can be determined whether the density fluctuation is caused by a slight change in the moisture content of the material or by other minor disturbance factors. When the cause is determined to be a slight change in the material's moisture content, the mapping relationship between the operating load information and the material's moisture content is adjusted by combining the density change information. When the problem is determined to be caused by other minor interference factors, a prompt message is issued to indicate the presence of minor interference factors.

8. The method according to claim 6, wherein the temperature and humidity of the biomass fuel pellet molding machine is controlled. When a lag occurs in the correlation between material moisture content and operating load information, the steps of acquiring the rate and direction of change of operating load information, using the rate and direction of change to predict the future trend of material moisture content, and adjusting the mapping relationship between operating load information and material moisture content based on the future trend include: When there is a lag in the correlation between material moisture content and operating load information, the rate and direction of change of operating load information should be continuously acquired. At the same time, real-time temperature and exhaust humidity information of the formed particles are obtained; Cross-compare the rate and direction of change of operating load information, the real-time temperature information of the formed particles, and the exhaust humidity information to identify whether there are signs of trend reversal. When signs of a trend reversal are detected, the mapping relationship between operating load information and material moisture content is adjusted based on the detected signs of a trend reversal.

9. The method of claim 6, wherein the temperature and humidity of the biomass fuel pellet molding machine is controlled by a temperature and humidity control device. The step of acquiring the fluctuation range of the molding temperature when it fluctuates, and compensating for and adjusting the mapping relationship between the operating load information and the moisture content of the material based on the fluctuation range to eliminate the influence of the molding temperature on the accuracy of the inference includes: Continuously monitor the fluctuation amplitude, frequency, and direction of the molding temperature; Based on the fluctuation amplitude, frequency, and direction of the molding temperature, and combined with a pre-set compensation model that reflects the influence of different temperature fluctuation characteristics on the mapping relationship between operating load information and material moisture content, the mapping relationship between operating load information and material moisture content is dynamically compensated and adjusted.

10. A temperature and humidity control system for a biomass fuel pellet forming machine, characterized in that, include: The material humidity information acquisition module is used to acquire material humidity information provided by the material humidity measuring device; The indirect physical feedback information acquisition module is used to acquire indirect physical feedback information, which includes the operating load information of the components driving the molding machine, the quality information of the molded particles, and the execution information of humidification adjustment. The operation status judgment module is used to judge the material humidity information, operating load information, quality information of shaped particles, and execution information of humidification adjustment, so as to identify the difference between the material humidity information and the indirect physical feedback information, and determine the operation status of the material humidity measuring device. The confidence level adjustment module is used to adjust the confidence level of the material humidity information when the operating status indicates that the material humidity measuring device has a deviation, and to obtain the material humidity adjustment value. The actual moisture content inference module is used to infer the actual moisture content of the material based on the operating load information. The humidification command issuing module is used to issue commands to adjust the humidification amount based on the material's actual moisture content and humidity adjustment value. The prompt message issuing module is used to issue a prompt message to the material humidity measuring device when the operating status indicates that there is a deviation in the material humidity measuring device.

Images