阅读说明：本技术 一种基于机器视觉及数据驱动的烧结生产方法 (Sintering production method based on machine vision and data driving ) 是由 王耀祖 贺威 张建良 刘征建 侯静怡 黄建强 马云飞 江回清 于 2021-07-13 设计创作，主要内容包括：本发明公开了一种基于机器视觉及数据驱动的烧结生产方法,包括：将各种烧结原料取样进行质量检测,记录不同种类烧结原料占比,并实时上传至烧结专家数据库；在烧结机尾部安装图像采集装置,采集到的图像通过红外热成像仪进行检测,得到烧结机尾部料层断面的温度、火红层厚度、火红层均一性指标,并实时上传；在烧结机尾部安装高光谱成像仪,检测烧结机尾部成品烧结矿的化学成分及尾部料层断面成分的均匀程度,并实时上传；在烧结冷却机出口处安装高清摄像机,检测成品烧结矿粒度变化,并实时上传；烧结专家数据库基于上传的各项数据进行数据挖掘及大数据分析,构建烧结生产过程智能控制系统,对烧结原料占比进行调控,以实现烧结过程闭环控制。(The invention discloses a sintering production method based on machine vision and data driving, which comprises the following steps: sampling various sintering raw materials, performing quality detection, recording the proportion of the sintering raw materials of different types, and uploading the proportion to a sintering expert database in real time; installing an image acquisition device at the tail of the sintering machine, detecting the acquired image by an infrared thermal imager to obtain the temperature of the material layer section at the tail of the sintering machine, the thickness of a scarlet layer and the uniformity index of the scarlet layer, and uploading the indexes in real time; installing a hyperspectral imager at the tail of the sintering machine, detecting the chemical components of finished sintered ores at the tail of the sintering machine and the uniformity of the components of the material layer section at the tail, and uploading the chemical components and the uniformity in real time; installing a high-definition camera at the outlet of the sintering cooler, detecting the granularity change of the finished sintered ore, and uploading the granularity change in real time; and the sintering expert database performs data mining and big data analysis based on various uploaded data, constructs an intelligent control system for the sintering production process, and regulates and controls the proportion of sintering raw materials so as to realize closed-loop control of the sintering process.)

1. A sintering production method based on machine vision and data driving is characterized by comprising the following steps:

sampling various sintering raw materials, performing quality detection, recording the proportion of the different sintering raw materials, and uploading result data to a sintering expert database in real time;

secondly, installing an image acquisition device and an infrared thermal imager at the tail part of the sintering machine, detecting the acquired image by the infrared thermal imager to obtain the temperature of the material layer section at the tail part of the sintering machine, the thickness of a scarlet layer and the uniformity index of the scarlet layer, and uploading the result data to a sintering expert database in real time;

thirdly, installing a hyperspectral imager at the tail of the sintering machine, detecting the chemical components of the finished sintered ore at the tail of the sintering machine and the uniformity of the components of the material layer section at the tail, and uploading the result data to a sintering expert database in real time;

installing a high-definition camera at the outlet of the sintering cooler, detecting the granularity change of the finished sintered ore, and uploading the result data to a sintering expert database in real time;

and fifthly, the sintering expert database performs data mining and big data analysis based on the received result data, constructs an intelligent control system for the sintering production process, and regulates and controls the proportion of sintering raw materials so as to realize closed-loop control of the sintering process.

2. The machine vision and data driven sintering production method according to claim 1, wherein the first step specifically comprises:

manually detecting and proportioning sintering raw materials, and manually inputting data into a sintering expert database;

an automatic sampling device is additionally arranged below a distributing roller of the sintering machine, the sintering mixture is sampled at variable time, the quality, the granularity and the proportion data are detected, and the raw material data in a sintering expert database are modified in real time.

3. The sintering production method based on machine vision and data drive as claimed in claim 1, wherein the image acquisition device used in the second step is an infrared detector.

4. The sintering production method based on machine vision and data driving as claimed in claim 3, wherein in the second step, a water cooling protection device is arranged around the infrared thermal imager, the infrared thermal imager converts the electronic video signal measured by the infrared detector into an infrared thermal image through a two-dimensional plane imaging infrared system, the infrared thermal image is displayed by a display for manual real-time viewing, the temperature, the thickness and the uniformity index of a scarlet layer of the sintering machine tail material layer are intelligently identified, and the result data are uploaded to a sintering expert database in real time.

5. The sintering production method based on machine vision and data driving according to claim 1, characterized in that in the third step, the hyperspectral imager is installed at the periphery of the infrared thermal imager, a water cooling protection device is arranged around the hyperspectral imager, the hyperspectral imager detects the spectrum signal of the sintering machine tail material layer section in real time based on a machine vision system, converts the spectrum signal into chemical components according to a spectrum library, and uploads the chemical components and distribution data of the sintering machine tail material layer section to a sintering expert database in real time.

6. The machine vision and data drive-based sintering production method according to claim 1, wherein in the fourth step, the detecting the particle size change of the finished sintered ore specifically comprises:

the high-definition camera is installed at the outlet of the sintering cooler, the shot image is sent to the sintering control room in real time, a group of high-definition pictures are shot at intervals of 10 seconds, the granularity composition of the sintered ore is calculated based on a machine vision system, and the result data is uploaded to a sintering expert database in real time.

7. The machine vision and data drive-based sintering production method according to claim 1, wherein in the step five, the working process of the constructed intelligent sintering production process control system comprises:

collecting various result data acquired in real time, performing data mining and big data analysis, calculating a solution when a problem occurs, uploading the solution to a sintering control room, and modifying the type and the ratio of sintering raw materials based on the solution.

8. The machine vision and data driven sintering production method based on claim 7 is characterized in that the modification mode comprises manual modification and system automatic modification.

Technical Field

The invention relates to the technical field of ferrous metallurgy, in particular to a sintering production method based on machine vision and data driving.

Background

In 2019, the pig iron yield of the blast furnace in China is 7.7 hundred million tons, and accounts for 62.2 percent of the pig iron yield (12.4 hundred million tons) in the world. The high-alkalinity agglomerate added with the acid pellet ore is the current furnace burden structure in China, the agglomerate accounts for 78% and the pellet ore accounts for about 13% (1.2 hundred million tons) in the furnace burden structure of the national blast furnace in 2019. Producing high-quality sinter, which is the basis of high quality and high yield of blast furnace smelting. However, the sintering quality parameters are complex and various, so the control of the sintering quality parameters is usually based on the observation of the tail and the section of the sintering machine and the corresponding control operation according to experience. At present, artificial intelligence and computer technology are developed vigorously, and a detection technology taking image processing as a core provides an advanced and accurate detection way for detecting the tail section of the sintering machine.

Most factories currently have industrial tv monitoring profiles, and in recent years image analysis techniques have been used for quantification. According to research, Kawasaki Steel works, Japan, uses an image analyzer to divide an image into 5 parts by the width of a trolley, and calculates the area of each red high-temperature zone of a sinter bed once per second. After the image analyzer is used, the yield and the quality of the sinter are obviously improved. The technology is researched and improved in China, and the recent Laiwu steel group cannot meet the functions of providing data support and judgment prediction for sintering operators due to the fact that the existing equipment cannot meet the requirements, equipment transformation is conducted on a 400m2 sintering machine tail thermal imager, advanced sintering machine tail thermal imager equipment can achieve prediction of FeO in a sintering ore on line, meanwhile, vertical sintering speed, end point analysis and temperature field distribution of a machine tail section are detected, changes of parameter indexes of the sintering ore are reflected visually by using data, the overall yield quality and stability of the sintering ore are improved, and more data analysis is provided for technical staff. Although various scientific research institutes and steel enterprises do a lot of work and applications on the tail section of the sintering machine, a lot of problems still exist: (1) the prediction of the FeO content in the sintering ore is inaccurate; (2) the section system has low identification precision, a self-learning system is difficult to realize, and an algorithm needs to be further improved.

The hyperspectral imaging technology is an image data technology based on very many narrow waves developed in the last two decades. The definition is that on the basis of multispectral imaging, in the spectral range from ultraviolet to infrared, an imaging spectrometer is utilized to continuously image a target object in dozens or hundreds of spectral bands in the spectral coverage range. The spectral information of the object to be measured is obtained while the spatial characteristic imaging of the object is obtained. Because the reflection spectrum of the object has a fingerprint effect, different objects have different spectrums, and different substance information can be distinguished by the principle that the same object has certain spectrum. At present, the hyperspectral imaging technology is mainly applied to the fields of agricultural food, medical drugs, aerospace, geological exploration and the like, but is less applied to the field of metallurgy. The technology can be matched with a sintering machine tail thermal imager, not only can the indexes of the vertical sintering speed, the end point analysis, the temperature field distribution and the like of the section of the machine tail be observed in real time, but also can detect the chemical components and the sintering uniformity of the section of the sintering section on line, reflect more parameter index changes of the sintering ore and enable sintering technicians to better control the sintering process.

In addition, physical properties such as strength and particle size of the sintered ore are also important indexes in quality inspection. Early sintering finished product detects mostly the manual sampling mode, and this mode is not only unsuitable present sintering production rhythm, and the system sample cycle length of getting influences the promptness of inspection, and the manual sampling environment is abominable moreover, the dust is many, the noise is big, intensity of labour is high, the potential safety hazard is big, influences that the workman is healthy. Along with the large-scale and modernization of iron and steel enterprises at home and abroad, the production process is increasingly high-speed and automatic, higher requirements are also put forward on the accuracy, the scientificity and the timeliness of the quality inspection of the sinter, and the adoption of the automatic inspection of the physical properties of the sinter finished product instead of manual quality inspection is imperative.

Although much work is done on sintering machine tail section imaging, particle size detection, chemical composition detection, sintering big data and the like, a closed-loop control system aiming at the sintering production process and selection of corresponding technical algorithms and matching among the technologies is not formed yet. Therefore, it is necessary to research a device technology based on the above and combine with big data analysis driving to realize intelligent control of sintering production process, provide important sintering data parameters and results for sintering workers, and improve sintering production stability and sintering mineral quality.

Disclosure of Invention

The invention aims to provide a sintering production method based on machine vision and data driving, and aims to solve the main problems of developing sintering intellectualization and unmanned property, acquiring more basic parameters influencing sintering behavior in the sintering production process in real time, particularly parameters which cannot be measured in real time by manual operation, realizing online detection of finished ore quality and instant optimization and adjustment of sintering process parameters, reducing the influence of manual operation on the sintering process in the sintering process, improving the quality of sintered ore and improving the working environment of sintering workers.

To solve the above technical problem, an embodiment of the present invention provides the following solutions:

a sintering production method based on machine vision and data driving comprises the following steps:

sampling various sintering raw materials, performing quality detection, recording the proportion of the different sintering raw materials, and uploading result data to a sintering expert database in real time;

secondly, installing an image acquisition device and an infrared thermal imager at the tail part of the sintering machine, detecting the acquired image by the infrared thermal imager to obtain the temperature of the material layer section at the tail part of the sintering machine, the thickness of a scarlet layer and the uniformity index of the scarlet layer, and uploading the result data to a sintering expert database in real time;

thirdly, installing a hyperspectral imager at the tail of the sintering machine, detecting the chemical components of the finished sintered ore at the tail of the sintering machine and the uniformity of the components of the material layer section at the tail, and uploading the result data to a sintering expert database in real time;

installing a high-definition camera at the outlet of the sintering cooler, detecting the granularity change of the finished sintered ore, and uploading the result data to a sintering expert database in real time;

and fifthly, the sintering expert database performs data mining and big data analysis based on the received result data, constructs an intelligent control system for the sintering production process, and regulates and controls the proportion of sintering raw materials so as to realize closed-loop control of the sintering process.

Preferably, the first step specifically includes:

manually detecting and proportioning sintering raw materials, and manually inputting data into a sintering expert database;

an automatic sampling device is additionally arranged below a distributing roller of the sintering machine, the sintering mixture is sampled at variable time, the quality, the granularity and the proportion data are detected, and the raw material data in a sintering expert database are modified in real time.

Preferably, the image acquisition device adopted in the second step is an infrared detector.

Preferably, in the second step, a water cooling protection device is arranged around the infrared thermal imager, the infrared thermal imager converts the electronic video signal measured by the infrared detector into an infrared thermal image through a two-dimensional plane imaging infrared system, the infrared thermal image is displayed by a display for manual real-time checking, the temperature, the thickness and the uniformity index of a scarlet layer of a material layer at the tail part of the sintering machine are intelligently identified, and result data are uploaded to a sintering expert database in real time.

Preferably, in the third step, the hyperspectral imager is installed at the periphery of the infrared thermal imager, a water cooling protection device is arranged around the hyperspectral imager, the hyperspectral imager detects the spectral signals of the material layer section at the tail of the sintering machine in real time based on a machine vision system, converts the spectral signals into chemical components according to a spectrum library, and uploads the chemical components and distribution data of the material layer section at the tail of the sintering machine to a sintering expert database in real time.

Preferably, in the fourth step, the detecting the particle size change of the finished sintered ore specifically includes:

the high-definition camera is installed at the outlet of the sintering cooler, the shot image is sent to the sintering control room in real time, a group of high-definition pictures are shot at intervals of 10 seconds, the granularity composition of the sintered ore is calculated based on a machine vision system, and the result data is uploaded to a sintering expert database in real time.

Preferably, in the fifth step, the working process of the constructed intelligent control system for the sintering production process includes:

collecting various result data acquired in real time, performing data mining and big data analysis, calculating a solution when a problem occurs, uploading the solution to a sintering control room, and modifying the type and the ratio of sintering raw materials based on the solution.

Preferably, the modification mode comprises manual modification and system automatic modification.

The technical scheme provided by the embodiment of the invention has the beneficial effects that at least:

in the embodiment of the invention, based on an image recognition technology and a big data mining technology, sintering machine tail section thermal imaging data are obtained in real time through a sintering machine tail infrared thermal imager, and indexes such as temperature, scarlet thickness and scarlet uniformity are obtained; meanwhile, acquiring chemical components of the sinter in real time by a hyperspectral on-line detection technology; acquiring the granularity change of the finished sintered ore in real time based on a high-definition camera; and finally, uploading the detection result and the quality of the sintering raw materials to a sintering expert database, constructing an intelligent control system in the sintering production process based on big data mining analysis, and realizing on-line detection of the granularity and chemical components of the sintering ore and instant optimization and adjustment of process parameters, thereby improving the quality of the sintering ore, reducing the influence of manual operation in the sintering process and finally realizing unmanned and intelligent sintering process.

In addition, the method greatly reduces the labor intensity of sintering workers, improves the working environment, ensures that the modification of sintering ore blending and the detection of sintering quality are more accurate and objective due to the reduction of human factors, can inquire the detection data in real time and is more favorable for guiding the production operation.

Drawings

In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.

FIG. 1 is a flow chart of a sintering production method based on machine vision and data driving according to an embodiment of the present invention;

fig. 2 is a schematic view of an equipment installation position in a sintering process according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail with reference to the accompanying drawings.

An embodiment of the present invention provides a sintering production method based on machine vision and data driving, as shown in fig. 1, the method includes the following steps:

sampling various sintering raw materials, performing quality detection, recording the proportion of the different sintering raw materials, and uploading result data to a sintering expert database in real time.

The method specifically comprises the following steps: manually detecting and proportioning sintering raw materials, and manually inputting data into a sintering expert database; an automatic sampling device is additionally arranged below a distributing roller of the sintering machine, the sintering mixture is sampled at variable time, the quality, the granularity and the proportion data are detected, and the raw material data in a sintering expert database are modified in real time.

And secondly, installing an image acquisition device and an infrared thermal imager at the tail part of the sintering machine, detecting the acquired image by the infrared thermal imager to obtain the temperature of the material layer section at the tail part of the sintering machine, the thickness of the scarlet layer and the uniformity index of the scarlet layer, and uploading the result data to a sintering expert database in real time.

In this step, the adopted image acquisition device is an infrared detector, and a water cooling protection device is arranged around the infrared thermal imager so as to reduce the influence of high temperature on the instrument. The infrared thermal imager converts an electronic video signal measured by an infrared detector into an infrared thermal image through a two-dimensional plane imaging infrared system, displays the infrared thermal image by a display for manual real-time checking, intelligently identifies indexes such as temperature, scarlet thickness, scarlet uniformity and the like of a sintering machine tail material layer section, and uploads result data to a sintering expert database in real time.

And thirdly, installing a hyperspectral imager at the tail of the sintering machine, detecting the chemical components of the finished sintered ore at the tail of the sintering machine and the uniformity of the components of the material layer section at the tail, and uploading the result data to a sintering expert database in real time.

In the step, the hyperspectral imager is installed at the periphery of the infrared thermal imager, the periphery of the hyperspectral imager is also provided with a water cooling protection device, the hyperspectral imager detects the spectral signals of the sintering machine tail material layer section in real time based on a machine vision system, converts the spectral signals into chemical components according to a spectrum library, and uploads the chemical components and distribution data of the sintering machine tail material layer section to a sintering expert database in real time.

And fourthly, installing a high-definition camera at the outlet of the sintering cooler, detecting the granularity change of the finished sintered ore, and uploading the result data to a sintering expert database in real time.

Wherein, detecting the particle size change of the finished sintered ore specifically comprises:

the high-definition camera is installed at the outlet of the sintering cooler, the shot image is sent to the sintering control room in real time, a group of high-definition pictures are shot at intervals of 10 seconds, the granularity composition of the sintered ore is calculated based on a machine vision system, and the result data is uploaded to a sintering expert database in real time.

And fifthly, the sintering expert database performs data mining and big data analysis based on the received result data, constructs an intelligent control system for the sintering production process, and regulates and controls the proportion of sintering raw materials so as to realize closed-loop control of the sintering process.

In this step, the working process of the constructed intelligent control system for the sintering production process comprises:

collecting various result data acquired in real time, performing data mining and big data analysis, calculating a solution when a problem occurs, uploading the solution to a sintering control room, and modifying the type and the ratio of sintering raw materials based on the solution. The modification modes comprise manual modification and system automatic modification.

In a specific embodiment, three kinds of mineral powder (A, B, C), limestone and anthracite are used as sintering raw materials, detection equipment is additionally arranged on a sintering production line of a certain iron and steel enterprise to carry out a demonstration sintering experiment, the chemical components and the proportion of the sintering raw materials are shown in tables 1 and 2, and a sintering proportion scheme simulates the actual industrial sintering production proportion of a sintering plant.

The equipment adding position in the sintering process is shown in figure 2, an automatic sampling device is arranged below the sintering distributing roller, an infrared thermal imager and a hyperspectral imager are additionally arranged at the tail part of the sintering machine, and a high-definition camera is additionally arranged at the outlet of a sintering cooler. All the detecting instruments are connected to a computer with a sintering expert database, and are uniformly detected and controlled by the computer.

TABLE 1 chemical composition Table of experimental raw materials for sintering

Name of raw materials	TFe	SiO2	CaO	MgO	Al2O3
						A mineral powder	66.50	5.82	0.44	0.45	0.46
B mineral powder	63.63	3.78	0.07	0.05	2.06
						C mineral powder	60.25	6.27	0.12	0.06	1.35
Limestone		2.1	50.35	4.22

TABLE 2 names and proportions of sintering raw materials

Name of raw materials	A mineral powder	B mineral powder	C mineral powder	Limestone	Anthracite coal
						Proportioning	27.4	34.5	16.5	16.0	5.6

1. Procedure of experiment

Before sintering production practice, for quality detection of sintering raw materials, chemical components and particle size composition detection is carried out on three mineral powder, limestone and anthracite, a raw material proportioning scheme is designed by simulating actual industrial sintering production proportioning of a certain sintering plant, and all data are input into a sintering expert database. In addition, sintering production data of the sintering plant in nearly three months is obtained, the data are uploaded to a sintering expert database, and a simple sintering big data computing platform is constructed.

After sintering production practice is started, detecting indexes such as temperature, thickness of a scarlet layer, uniformity of the scarlet layer and the like of the sintering machine tailing material layer section by using an infrared thermal imager at the tail of the sintering machine; detecting the chemical components of the finished sintered ore at the tail of the sintering machine and the uniformity of the components of the material layer section at the tail by using a hyperspectral imager; a high-definition camera is additionally arranged at the outlet of the sintering cooler to detect the granularity change of the finished sintered ore; the detection data are summarized and then input into a sintering expert database in real time, and data and calculation parameters are provided for a calculation platform.

After the big data computing platform calculates to obtain the best result, the proportioning data and the prediction result are displayed on a computer display interface, and sintering workers can select to automatically or manually change the proportioning.

2. Results and analysis of the experiments

Because the actual sintering production of the sintering plant uses the fluxes of limestone and quicklime, the fuel uses coke powder and anthracite, and the flux used in the demonstration sintering production only uses the limestone and the fuel only uses the anthracite, the granularity composition and the drum strength of the finished ore produced by sintering have larger difference with the quality of the finished ore produced by actual sintering.

The data transmitted by a high-definition camera at the tail part of the sintering cooler shows that the percentage of the sintered ore with the granularity of less than 10mm is 41.3 percent, the granularity composition is poor, three groups of samples are taken from the finished ore to carry out the drum strength detection, and the average drum strength is 70.6 percent. The infrared thermal imaging instrument detects that the uniformity of a fire red layer of the sintering machine tail section is poor, the sintered ore at the top of the material layer is seriously overfired, and the sintered ore at the bottom of the material layer has a light burning trend. The high spectrum imager at the tail part of the sintering machine detects that the chemical composition and the uniformity in the middle of the section of the tail part of the sintering machine are better, and the chemical composition and the uniformity of the sections at the top and the bottom of the sintering machine are poorer.

After uploading the near-term data to a sintering expert database, analyzing by using a self-built big data computing platform to obtain a new sintering raw material proportioning scheme, wherein the modified scheme is shown in Table 3, the proportioning of the low-silicon B mineral powder is reduced to improve the integral SiO2 content, meanwhile, the limestone content is increased to correct the alkalinity, and the raw material proportioning is properly reduced to reduce the influence of the overburning of the sintering ore. The sintering expert database sends the modification scheme to a display screen for a sintering worker to check, the ratio of sintering raw materials is automatically changed after permission, and the sintering worker is reminded to adjust a batching structure.

Table 3 modified names and proportions of sintering raw materials

Name of raw materials	A mineral powder	B mineral powder	C mineral powder	Limestone	Anthracite coal
						Proportioning	28.6	32.4	17.3	16.9	4.8

And (4) modifying the sintering raw material ratio through a big data computing platform, adjusting a distributing roller by a sintering worker to change the structure of the sintering raw material, and performing the demonstration sintering experiment again. The sintering results are: the data transmitted by a high-definition camera at the tail part of the sintering cooler shows that the percentage of the sintering ore with the granularity of less than 10mm is 50.5 percent, and the granularity composition is obviously improved; three groups of samples of the finished ore are taken for drum strength detection, and the average drum strength is 75.6%; the infrared thermal imaging instrument detects that the uniformity of a fire red layer of the sintering machine tail section is also obviously improved, the overburning tendency of the sintering ore at the top of the material layer is reduced, and the sintering ore at the bottom has no light burning tendency; the hyperspectral imager at the tail of the sintering machine detects that the middle part and the bottom of the section of the tail of the sintering machine have better chemical compositions and uniformity, and the chemical compositions and uniformity at the top of the sintering machine are also obviously improved.

In conclusion, based on the image recognition technology and the big data mining technology, the sintering machine tail section thermal imaging data are obtained in real time through the sintering machine tail infrared thermal imager, and indexes such as temperature, scarlet thickness and scarlet uniformity are obtained; meanwhile, acquiring chemical components of the sinter in real time by a hyperspectral on-line detection technology; acquiring the granularity change of the finished sintered ore in real time based on a high-definition camera; and finally, uploading the detection result and the quality of the sintering raw materials to a sintering expert database, constructing an intelligent control system in the sintering production process based on big data mining analysis, and realizing on-line detection of the granularity and chemical components of the sintering ore and instant optimization and adjustment of process parameters, thereby improving the quality of the sintering ore, reducing the influence of manual operation in the sintering process and finally realizing unmanned and intelligent sintering process.

In addition, the method greatly reduces the labor intensity of sintering workers, improves the working environment, ensures that the modification of sintering ore blending and the detection of sintering quality are more accurate and objective due to the reduction of human factors, can inquire the detection data in real time and is more favorable for guiding the production operation.

The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.